CoChat
Sign Up
Cited by 18Generative Adversarial Networks and Image SynthesisComputer Graphics and Visualization Techniques3D Shape Modeling and Analysis

WorldScore: A Unified Evaluation Benchmark for World Generation

Open access
Duan, Haoyi, Yu, Hong–Xing, Chen, Sirui, Fei–Fei, Li, Wu, Jiajun·2025·2025 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv51701.2025.02573
Open this paper in CoChat — free accountOpen PDF

Abstract

We introduce the WorldScore benchmark, the first unified benchmark for world generation. We decompose world generation into a sequence of next-scene generation tasks with explicit camera trajectory-based layout specifications, enabling unified evaluation of diverse approaches from 3D and 4D scene generation to video generation models. The WorldScore benchmark encompasses a curated dataset of 3,000 test examples that span diverse worlds: static and dynamic, indoor and outdoor, photorealistic and stylized. The WorldScore metrics evaluate generated worlds through three key aspects: controllability, quality, and dynamics. Through extensive evaluation of 19 representative models, including both open-source and closed-source ones, we reveal key insights and challenges for each category of models. Our dataset, evaluation code, and leaderboard can be found at https://haoyi-duan.github.io/WorldScore/

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/iccv51701.2025.02573

Cites

0 of 98 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Cosmos-Predict1 and Cosmos-Transfer1 have facilitated the development of open evaluation benchmarks for general-purpose world generation and specialized domains such as physics and Embodied AI.

    “It has facilitated the development of open evaluation benchmarks for both general-purpose world generation (Duan et al., 2025; Zhou et al., 2025; Zhao et al., 2025) and specialized domains such as physics (Bansal et al., 2024; Motamed et al., 2025; Guo et al., 2025; Bansal et al., 2025; Bordes et al., 2025) and Embodied AI (Yang et al., 2025; Liao et al., 2025; Yue et al., 2025).”

    From World Simulation with Video Foundation Models for Physical AI (2025) · cites this paper as Duan et al., 2025

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

  • Image quality assessment: from error visibility to structural similarity

    Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works

  • The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

    Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623 · cited 1× · see citing works

    “Specifically, given two consecutive frames A and B , we first track a set of center-cropped points p A from frame A to frame B using forward optical flow F A → B : (S4)”

  • A Style-Based Generator Architecture for Generative Adversarial Networks

    Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · see citing works

  • Structure-from-Motion Revisited

    Schonberger, J. L., & Frahm, J.-M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.445 · Cited by 6,433 · cited 1× · see citing works

    “Unlike sparse methods such as COLMAP [60, 61], which rely on selecting “good” feature matches while discarding the rest, DROID-SLAM employs a differentiable Dense Bundle Adjustment (DBA) layer.”

  • Analyzing and Improving the Image Quality of StyleGAN

    Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332 · see citing works

  • A Neural Algorithm of Artistic Style

    Gatys, L., Ecker, A., & Bethge, M. (2016) · Journal of Vision · doi:10.1167/16.12.326 · Cited by 2,612 · cited 1× · see citing works

    “Style consistency: We evaluate the style consistency by computing the differences (F-norm) between the Gram matrices [17] of the first frame and the last frame of a single next-scene generation task.”

  • Taming Transformers for High-Resolution Image Synthesis

    Esser, P., Rombach, R., & Ommer, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01268 · Cited by 2,514 · see citing works

  • Pixelwise View Selection for Unstructured Multi-View Stereo

    Schönberger, J. L., Zheng, E., Frahm, J., & Pollefeys, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_31 · Cited by 2,331 · cited 1× · see citing works

    “Unlike sparse methods such as COLMAP [60, 61], which rely on selecting “good” feature matches while discarding the rest, DROID-SLAM employs a differentiable Dense Bundle Adjustment (DBA) layer.”

  • Scalable Diffusion Models with Transformers

    Peebles, W., & Xie, S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00387 · Cited by 2,284 · see citing works

  • Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection

    Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Jiang, Q., Li, C., Yang, J., Su, H., et al. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72970-6_3 · Cited by 2,074 · see citing works

  • SUN RGB-D: A RGB-D scene understanding benchmark suite

    Song, S., Lichtenberg, S. P., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298655 · Cited by 1,943 · cited 2× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • Matterport3D: Learning from RGB-D Data in Indoor Environments

    Chang, A., Dai, A., Funkhouser, T., Halber, M., Niebner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00081 · Cited by 1,858 · cited 2× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

    Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., & Zhao, H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00987 · Cited by 1,296 · cited 1× · see citing works

    “These meth-ods [11, 12, 24, 91] project the synthesized 2D scene extensions into a 3D representation by leveraging depth estimation models [4, 34, 37, 87].”

  • CLIPScore: A Reference-free Evaluation Metric for Image Captioning

    Hessel, J., Holtzman, A., Forbes, M., Le Bras, R., & Choi, Y. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.595 · Cited by 1,232 · cited 1× · see citing works

    “Content alignment: Besides the objects (which typically occupies approximately only of the text prompt length), we also assess whether the generated scenes are aligned with the entire text N using CLIPScore [22].”

  • Alias-Free Generative Adversarial NetworksPreprint

    Karras, T., Aittala, M., Laine, S., Härkönen, E., Hellsten, J., Lehtinen, J., & Aila, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.12423 · Cited by 1,226 · cited 1× · see citing works

    “Recent advances in image generation, including VAEs [36], GANs [5, 18, 30–33, 49], VQ approaches”

  • MUSIQ: Multi-scale Image Quality Transformer

    Ke, J., Wang, Q., Wang, Y., Milanfar, P., & Yang, F. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00510 · Cited by 1,048 · see citing works

  • A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos

    Schops, T., Schonberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., & Geiger, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.272 · Cited by 915 · cited 2× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • Exploring CLIP for Assessing the Look and Feel of Images

    Wang, J., Chan, K. C. K., & Loy, C. C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25353 · Cited by 795 · see citing works

  • Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

    Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R. C., & Schindler, K. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00907 · Cited by 444 · see citing works

  • VBench: Comprehensive Benchmark Suite for Video Generative Models

    Huang, Z., He, Y., Yu, J., Zhang, F., Si, C., Jiang, Y., Zhang, Y., Wu, T., Jin, Q., Chanpaisit, N., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02060 · Cited by 407 · cited 6× · see citing works

    “Existing consistency metrics, such as those with CLIP or DINO features [26, 27], focus on categorical identity but fail to capture fine-grained texture changes.”
    Influential

  • Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

    Roberts, M., Ramapuram, J., Ranjan, A., Kumar, A., Bautista, M. A., Paczan, N., Webb, R., & Susskind, J. M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01073 · Cited by 358 · cited 2× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

    Chen, H., Zhang, Y., Cun, X., Xia, M., Wang, X., Weng, C., & Shan, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00698 · Cited by 257 · cited 3× · see citing works

    “The progress of both open-source [1, 10, 84, 88] and closed-source [2, 6, 20, 58] video generation models has stimulated the proposal of numerous benchmarks [15, 26, 45, 46, 48, 92].”

  • LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

    Wang, Y., Chen, X., Ma, X., Zhou, S., Huang, Z., Yang, C., Yang, C., He, Y., Yu, J., Yang, P., et al. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02295-1 · Cited by 218 · see citing works

  • Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models

    Höllein, L., Cao, A., Owens, A., Johnson, J., & Nießner, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00727 · Cited by 167 · cited 2× · see citing works

    “These meth-ods [11, 12, 24, 91] project the synthesized 2D scene extensions into a 3D representation by leveraging depth estimation models [4, 34, 37, 87].”

  • MotionCtrl: A Unified and Flexible Motion Controller for Video Generation

    Wang, Z., Yuan, Z., Wang, X., Li, Y., Chen, T., Xia, M., Luo, P., & Shan, Y. (2024) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3641519.3657518 · Cited by 153 · cited 1× · see citing works

    “Recent work in injecting camera conditioning [21, 81] might be a promising solution.”

  • DynamiCrafter: Animating Open-Domain Images with Video Diffusion Priors

    Xing, J., Xia, M., Zhang, Y., Chen, H., Yu, W., Liu, H., Liu, G., Wang, X., Shan, Y., & Wong, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72952-2_23 · Cited by 149 · see citing works

  • EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

    Liu, Y., Cun, X., Liu, X., Wang, X., Zhang, Y., Chen, H., Liu, Y., Zeng, T., Chan, R., & Shan, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02090 · Cited by 121 · cited 3× · see citing works

    “The progress of both open-source [1, 10, 84, 88] and closed-source [2, 6, 20, 58] video generation models has stimulated the proposal of numerous benchmarks [15, 26, 45, 46, 48, 92].”

  • Towards Streaming Perception

    Li, M., Wang, Y.-X., & Ramanan, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58536-5_28 · Cited by 120 · cited 1× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • Aligning Latent and Image Spaces to Connect the Unconnectable

    Skorokhodov, I., Sotnikov, G., & Elhoseiny, M. (2021) · IEEE International Conference on Computer Vision · doi:10.1109/iccv48922.2021.01388 · Cited by 106 · cited 2× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

    Wang, Y., Lipson, L., & Deng, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72667-5_3 · Cited by 91 · see citing works

  • Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models

    Ling, H., Kim, S. W., Torralba, A. B., Fidler, S., & Kreis, K. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00819 · Cited by 72 · cited 1× · see citing works

    “To incorporate dynamics, 4D generation methods [39, 43, 56, 66, 95, 96, 96] further integrate multi-view and video diffusion priors.”

  • 4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

    Bahmani, S., Skorokhodov, I., Rong, V., Wetzstein, G., Guibas, L. J., Wonka, P., Tulyakov, S., Park, J. J., Tagliasacchi, A., & Lindell, D. B. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00764 · Cited by 63 · cited 4× · see citing works

    “When extended to 4D for dynamics, 4D-fy [3] does not perform well, likely due to the intrinsic difficulty in 4D scene generation.”
    Influential

  • Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing

    Zhu, J., Luan, F., Huo, Y., Lin, Z., Zhong, Z., Xi, D., Wang, R., Bao, H., Zheng, J., & Tang, R. (2022) · SIGGRAPH Asia Conference Papers · doi:10.1145/3550469.3555407 · Cited by 55 · cited 2× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • WonderJourney: Going from Anywhere to Everywhere

    Yu, H.-X., Duan, H., Hur, J., Sargent, K., Rubinstein, M., Freeman, W. T., Cole, F. H., Sun, D., Snavely, N., Wu, J., et al. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00636 · Cited by 55 · cited 7× · see citing works

    “Recent 3D scene generation models rely mainly on generative diffusion models [16, 90], which formulate generating scenes in a sequential manner using supervision from 2D image outpainting models.”
    InfluentialSelf-citation

  • Perspective Fields for Single Image Camera Calibration

    Jin, L., Zhang, J., Hold-Geoffroy, Y., Wang, O., Blackburn-Matzen, K., Sticha, M., & Fouhey, D. F. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01660 · Cited by 54 · cited 1× · see citing works

    “To ensure appropriate viewpoint composition, we utilize the Perspective Fields [28] to model the local perspective properties ( e.g ., yaw, pitch, and FOV).”

  • WonderWorld: Interactive 3D Scene Generation from a Single Image

    Yu, H.-X., Duan, H., Herrmann, C., Freeman, W. T., & Wu, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00555 · Cited by 53 · cited 7× · see citing works

    “Additionally, we evaluate six well-known 3D scene generation models: SceneScape [16], Text2Room [24], Lu-cidDreamer [11], WonderJourney [90], InvisibleStitch [12], and WonderWorld [91].”
    InfluentialSelf-citation

  • EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes

    Lê, H.-Â., Mensink, T., Das, P., Karaoğlu, S., & Gevers, T. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00162 · Cited by 27 · cited 2× · see citing works

    “Then, we source images from open-source scene datasets [8, 38, 42, 57, 62, 67, 69, 74, 98] and supplement with an online source, Unsplash [7].”

  • T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

    Sun, K., Huang, K., Xian, L., Wu, Y., Xu, Z., Li, Z., & Liu, X. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00787 · Cited by 19 · cited 1× · see citing works

    “TC-Bench [15] 150 ✗ ✗ ✗ ✓ ✗ ✗ ✗ EvalCrafter [45] 700 ✗ ✗ ✗ ✗ ✗ ✗ ✗ FETV [46] 619 ✗ ✗ ✗ ✗ ✗ ✗ ✗ VBench [26] 800 [71] 700 ✗ ✗ ✗ ✗ ✗ ✗ ✗ Meng et al. [48] 160 ✗ ✗ ✗ ✗ ✗ ✗ ✗ Wang et al. [78] 423 [92] 1649 [40] 350 Table 1.”

  • Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation

    Wang, Y., He, X., Wang, K., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01272 · Cited by 2 · cited 1× · see citing works

    “TC-Bench [15] 150 ✗ ✗ ✗ ✓ ✗ ✗ ✗ EvalCrafter [45] 700 ✗ ✗ ✗ ✗ ✗ ✗ ✗ FETV [46] 619 ✗ ✗ ✗ ✗ ✗ ✗ ✗ VBench [26] 800 [71] 700 ✗ ✗ ✗ ✗ ✗ ✗ ✗ Meng et al. [48] 160 ✗ ✗ ✗ ✗ ✗ ✗ ✗ Wang et al. [78] 423 [92] 1649 [40] 350 Table 1.”

  • Cosmos world foundation model platform for physical ai

    Agarwal (2025) · arXiv preprint

    Unresolved

  • Luma dream machine: New freedoms of imagination, 2025

    AI (2025)

    Unresolved

  • Zoedepth: Zero-shot transfer by combining relative and metric depth

    Bhat (2023) · arXiv preprint

    Unresolved

  • Large scale gan training for high fidelity natural image synthesis

    Brock (2018) · arXiv preprint

    Unresolved

  • Video generation models as world simulators

    Brooks (2024)

    Unresolved

  • Unsplash

    (2013)

    Unresolved

  • Videocrafter1: Open diffusion models for high-quality video generation

    Chen (2023)

    Unresolved

  • Luciddreamer: Domain-free generation of 3d gaussian splatting scenes

    Chung (2023) · arXiv preprint

    Unresolved

  • Invisible stitch: Generating smooth 3d scenes with depth inpainting

    Engstler (2024) · arXiv preprint

    Unresolved

  • Vchitect-2.0: Parallel transformer for scaling up video diffusion models

    Fan (2025) · arXiv preprint

    Unresolved

  • Tc-bench: Benchmarking temporal compositionality in text-to-video and image-to-video generation

    Feng (2024) · arXiv preprint

    Unresolved

  • Scenescape: Text-driven consistent scene generation

    Fridman (2024) · Advances in Neural Information Processing Systems

    Unresolved

  • Generative adversarial nets

    Goodfellow (2014) · Advances in neural information processing systems

    Unresolved

  • Ltx-video: Realtime video latent diffusion

    HaCohen (2024) · arXiv preprint

    Unresolved

  • HailuoAI

    (2024) · Hailuo

    Unresolved

  • Cameractrl: Enabling camera control for text-to-video generation

    He (2024) · arXiv preprint

    Unresolved

  • Denoising diffusion probabilistic models

    Ho (2020) · Advances in neural information processing systems

    Unresolved

  • Cogvideo: Large-scale pretraining for text-to-video generation via transformers

    Hong (2022) · arXiv preprint

    Unresolved

  • Vbench++: Comprehensive and versatile benchmark suite for video generative models

    Huang (2024) · arXiv preprint

    Unresolved

  • How far is video generation from world model: A physical law perspective

    Kang (2024) · arXiv preprint

    Unresolved

  • Progressive growing of gans for improved quality, stability, and variation

    Karras (2017) · arXiv preprint

    Unresolved

  • Auto-encoding variational bayes

    Kingma (2013) · arXiv preprint

    Unresolved

  • Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer

    Lasinger (2019) · arXiv preprint

    Unresolved

  • Vividdream: Generating 3d scene with ambient dynamics

    Lee (2024) · arXiv preprint

    Unresolved

  • Worldmodelbench: Judging video generation models as world models

    Li (2025) · arXiv preprint

    Unresolved

  • T2v-turbo: Breaking the quality bottleneck of video consistency model with mixed reward feedback

    Li (2024) · arXiv preprint

    Unresolved

  • Fetv: A benchmark for fine-grained evaluation of open-domain text-to-video generation

    Liu (2024) · Advances in Neural Information Processing Systems

    Unresolved

  • Videofusion: Decomposed diffusion models for highquality video generation

    Luo (2023) · arXiv preprint

    Unresolved

  • Towards world simulator: Crafting physical commonsense-based benchmark for video generation

    Meng (2024) · arXiv preprint

    Unresolved

  • Conditional generative adversarial nets

    Mirza (2014) · arXiv preprint

    Unresolved

  • Openvid-1m: A large-scale high-quality dataset for text-tovideo generation

    Nan (2024) · arXiv preprint

    Unresolved

  • OpenAI

    (2024) · Hello gpt-4o

    Unresolved

  • Learning transferable visual models from natural language supervision

    Radford (2021)

    Unresolved

  • Sam 2: Segment anything in images and videos

    Ravi (2024) · arXiv preprint

    Unresolved

  • Recraft image generation and editing api

    (2025)

    Unresolved

  • Dreamgaussian4d: Generative 4d gaussian splatting

    Ren (2023) · arXiv preprint

    Unresolved

  • Introducing gen-3 alpha: A new frontier for video gneration

    (2024)

    Unresolved

  • Large-scale classification of fine-art paintings: Learning the right metric on the right feature

    Saleh (2015) · arXiv preprint

    Unresolved

  • Christoph Schuhmann

    (2022) · Clip+ mlp aesthetic score predictor. Clip+ mlp aesthetic score predictor

    Unresolved

  • SDXL

    (2023) · 106 styles for stable diffusion xl model

    Unresolved

  • Make-a-video: Text-to-video generation without text-video data

    Singer (2022) · arXiv preprint

    Unresolved

  • Text-to-4d dynamic scene generation

    Singer (2023) · arXiv preprint

    Unresolved

  • Deep unsupervised learning using nonequilibrium thermodynamics

    Sohl-Dickstein (2015)

    Unresolved

  • Score-based generative modeling through stochastic differential equations

    Song (2020) · arXiv preprint

    Unresolved

  • Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras

    Teed (2021) · Advances in neural information processing systems

    Unresolved

  • Neural discrete representation learning

    Van (2017) · Advances in neural information processing systems

    Unresolved

  • Diode: A dense indoor and outdoor depth dataset

    Vasiljevic (2019) · arXiv preprint

    Unresolved

  • Modelscope text-to-video technical report

    Wang (2023) · arXiv preprint

    Unresolved

  • Q-align: Teaching l \text{mms} for visual scoring via discrete text-defined levels

    Wu (2023) · arXiv preprint

    Unresolved

  • Pandora: Towards general world model with natural language actions and video states

    Xiang (2024) · arXiv preprint

    Unresolved

  • Comp4d: Llm-guided compositional 4d scene generation

    Xu (2024) · arXiv preprint

    Unresolved

  • Easyanimate: A high-performance long video generation method based on transformer architecture

    Xu (2024) · arXiv preprint

    Unresolved

  • Cogvideox: Text-to-video diffusion models with an expert transformer

    Yang (2024) · arXiv preprint

    Unresolved

  • 4real: Towards photorealistic 4d scene generation via video diffusion models

    Yu (2024) · arXiv preprint

    Unresolved

  • Chronomagic-bench: A benchmark for metamorphic evaluation of text-to-time-lapse video generation

    Yuan (2024) · arXiv preprint

    Unresolved

  • Vfimamba: Video frame interpolation with state space models

    Zhang (2024) · arXiv preprint

    Unresolved

  • Animate 124: Animating one image to 4d dynamic scene

    Zhao (2023) · arXiv preprint

    Unresolved

  • A unified approach for textand image-guided 4d scene generation

    Zheng (2024)

    Unresolved

  • Allegro: Open the black box of commercial-level video generation model

    Zhou (2024) · arXiv preprint

    Unresolved

Flagged first, then by citations

59 of the 98 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Authors
Duan, H., Yu, H., Chen, S., Fei–Fei, L., & Wu, J.
Affiliations
  • Stanford University (US)
  • Stanford University
ORCID
Venue
2025 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2025-10-19
Pages
01-12
DOI
10.1109/iccv51701.2025.02573
OpenAlex
W4417232068
Semantic Scholar
d6a5f0339ddf541482b39ab4e25d670191ef1903
Cited by
17
References
98
Citations by year
2026: 16 · 2025: 1
FWCI
12.85
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
  • Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
Keywords
benchmark, 3D scene generation, video generation, camera trajectory, controllability, dynamic scenes, photorealistic rendering, stylized rendering, evaluation metrics

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review