arXiv AI
Jul 7
Motion Attribution for Video Generation
arXiv:2601. 08828v2 Announce Type: replace-cross Abstract: Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood.
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
arXiv:2606. 30248v1 Announce Type: cross Abstract: Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.
Related stories
arXiv Computer Vision
2d ago
VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation
VTR-Bench is a new benchmark designed to evaluate how well video generation models render text within scenes. It includes 300 prompts across five real-world scenarios such as advertisements and scientific videos, and uses an automated pipeline with human alignment to assess text fidelity and scene/motion requirements. Experiments on 11 state‑of‑the‑art models show that even the best performer has a word error rate of 0.250, underscoring widespread challenges in visual text rendering.
arXiv Computer Vision
4d ago
CurvSpec: Adaptive Multi-Curvature Learning for Partial Relevant Video Retrieval
arXiv:2609.36815v1 Announce Type: new Abstract: Partially Relevant Video Retrieval (PRVR) seeks to retrieve untrim-med videos containing a moment that matches a text query, without temporal annotatio...
arXiv Computer Vision
Aug 31
Video Generative Models as Geometry Learner
The paper introduces GeoNeXt, a framework that repurposes pretrained video generative models for geometry estimation by framing it as a next‑frame prediction task. Unlike prior methods that either train separate depth/normal models or fine‑tune image diffusion backbones, GeoNeXt jointly models images and geometric targets, leveraging the structured knowledge of video models for more data‑efficient learning. Experiments show zero‑shot monocular depth and surface normal estimation that outperforms existing generative approaches and rivals discriminative state‑of‑the‑art methods while using far less training data.
arXiv Machine Learning
Jun 9
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation
arXiv:2606. 09056v1 Announce Type: cross Abstract: Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence lengths.
arXiv Computer Vision
4d ago
GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space
arXiv:2609.35734v2 Announce Type: replace Abstract: Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, whi...
arXiv Computer Vision
Aug 31
Manifold4D: Denoising on Point Cloud Rendered Manifolds for Video Re-shooting
Manifold4D introduces a new denoising strategy for video re‑shooting that injects a rendered point‑cloud directly into the initial noise manifold, eliminating the need for the render to be an explicit conditioning stream during denoising. This approach allows the network to rely solely on the source video as a visual condition, improving camera‑control accuracy on the DAVIS‑Traj benchmark and Vista4D set, with significant reductions in rotation and translation errors while maintaining video fidelity. User studies confirm enhanced trajectory following and dynamic consistency, especially for large yaw amplitudes and even when the render is corrupted.
arXiv AI
Jun 9
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
arXiv:2601. 23286v4 Announce Type: replace-cross Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift.
arXiv AI
4d ago
CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models
CoRe introduces a co‑evolving reward framework to mitigate latent reward hacking in video diffusion models. By continuously refitting the latent‑reward model on the generator’s current samples and anchoring it to real‑video preferences, CoRe prevents the generator from drifting outside the reward model’s training support. Experiments on Wan2.1‑T2V‑1.3B demonstrate that CoRe improves generation quality over pretrained models and prior alignment methods while avoiding quality collapse.
arXiv AI
Jun 30
MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
arXiv:2606. 29531v1 Announce Type: cross Abstract: We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs.
arXiv Computer Vision
Sep 10
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
arXiv:2605.12957v2 Announce Type: replace Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
arXiv Computer Vision
Sep 4
WorldReward: Reward Modeling for Camera-Conditioned World Models
WorldReward introduces a vision‑language model–based reward system for camera‑conditioned world models, combining action consistency and visual quality evaluation. It processes paired videos by splitting them into action‑aligned chunks, structuring visual evidence, and aggregating decisions through voting. The model is trained on a large, reasoning‑augmented preference dataset and outperforms GPT‑5.5 on a human‑annotated benchmark, improving both action execution and visual quality when applied to RL post‑training.