Papers20

#temporal consistency

Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

Shaocong Xu, Songlin Wei et al.Dec 29arXiv

Transparent and shiny objects confuse normal depth cameras, but video diffusion models already learned how light bends and reflects through them.

#video diffusion model#transparent object depth#normal estimation

The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text

Intermediate

Hanlin Wang, Hao Ouyang et al.Dec 18arXiv

WorldCanvas lets you make videos where things happen exactly how you ask by combining three inputs: text (what happens), drawn paths called trajectories (when and where it happens), and reference images (who it is).

#WorldCanvas#promptable world events#trajectory-controlled video generation

PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence

Intermediate

Xiaopeng Lin, Shijie Lian et al.Dec 18arXiv

Robots learn best from what they would actually see, which is a first-person (egocentric) view, but most AI models are trained on third-person videos and get confused.

#egocentric vision#first-person video#vision-language model

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

Intermediate

Yuwei Guo, Ceyuan Yang et al.Dec 17arXiv

This paper fixes a common problem in video-making AIs where tiny mistakes snowball over time and ruin long videos.

#autoregressive video diffusion#exposure bias#teacher forcing

IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learning

Intermediate

Yuanhang Li, Yiren Song et al.Dec 17arXiv

IC-Effect is a new way to add special effects to existing videos by following a text instruction while keeping everything else unchanged.

#video editing#visual effects#diffusion transformer

MMGR: Multi-Modal Generative Reasoning

Intermediate

Zefan Cai, Haoyi Qiu et al.Dec 16arXiv

MMGR is a new benchmark that checks whether AI image and video generators follow real-world rules, not just whether their outputs look pretty.

#multi-modal generative reasoning#video generation evaluation#physical commonsense

LongVie 2: Multimodal Controllable Ultra-Long Video World Model

Intermediate

Jianxiong Gao, Zhaoxi Chen et al.Dec 15arXiv

LongVie 2 is a video world model that can generate controllable videos for 3–5 minutes while keeping the look and motion steady over time.

#long video generation#world model#multimodal control

VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory

Beginner

Yifei Yu, Xiaoshan Wu et al.Dec 4arXiv

VideoSSM is a new way to make long, stable, and lively videos by giving the model two kinds of memory: a short-term window and a long-term state-space memory.

#autoregressive video diffusion#state-space model#hybrid memory

1 2