The paper introduces Motion Estimation-based Video Convolution (MEVC), a framework that removes the need for image signal processors by operating directly on raw Bayer pixel data. MEVC incorporates sliding‑window motion estimation into each convolutional layer, allowing prediction and residual refinement to cut redundant computations across frames. The resulting end‑to‑end pipeline achieves more than 70% reduction in FLOPs while maintaining accuracy on video semantic segmentation, depth estimation, and object detection tasks.
By Haichao Wang, Jiangtao Wen, Yuxing Han
arXiv:2607.10495v2 Announce Type: replace
Abstract: Recent Video Super-Resolution (VSR) methods rely heavily on transformers and explicit optical flow, creating computational overhead and custom oper...
By Filip Pawlicki, Marcel Ka\'ndu{\l}a, Marcin Pucek, Kamil Dobies
arXiv:2605. 03337v3 Announce Type: replace-cross Abstract: Recent progress in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction results.
By Lucas Yunkyu Lee, Soonho Kim, Youngwook Kim, Sangmin Kim, Jaesik Park
arXiv:2608.20770v1 Announce Type: new
Abstract: Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does...
By Haojin He, Hao Tan, Zichang Tan, Ajian Liu, Jun Wan
arXiv:2608.22861v1 Announce Type: new
Abstract: State Space Models (SSMs) have surfaced as a promising architecture in Video Frame Interpolation (VFI), as they can capture long-range dependencies wit...
By Jaehyun Park, Nam Ik Cho
arXiv:2608.27584v1 Announce Type: new
Abstract: Autonomous systems rely on extracting information from light, yet remain brittle in extreme environments, from nighttime navigation to high-speed robot...
By Varun Sundar, Pavan Thodima, Sacha Jungerman, Mohit Gupta
The paper introduces a new framework for estimating full-degree-of-freedom egomotion directly from asynchronous optical flow captured by event cameras. By decoupling the differential epipolar constraint into angular and linear components and applying a first-order approximation, the authors derive a polynomial formulation that yields the first algebraic minimal 5‑point solver for this problem. An accelerated solver that truncates high‑order angular velocity terms is also proposed, enabling real‑time performance in high‑speed scenarios, and extensive tests show superior accuracy and robustness compared to traditional synchronous methods.
By Shuo Pan, Banglei Guan, Bin Li, Zhenbao Yu, Zibin Liu, Zi Wang, Yang Shang, Qifeng Yu
arXiv:2608.21828v1 Announce Type: new
Abstract: Novel-view synthesis of dynamic scenes, crucial for AR/VR applications, remains a challenging problem. Recent methods adapt representations like 3D Gau...
By Ankit Dhiman, Kunal A Kathare, Pranav Vignesh, Lokesh R Boregowda, Venkatesh Babu Radhakrishnan
Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos.
arXiv:2604. 22160v2 Announce Type: replace-cross Abstract: Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation.
By Eric Li, Arijit Dasgupta, Yoni Friedman, Mathieu Huot, Vikash Mansinghka, Thomas O'Connell, William T. Freeman, Joshua B. Tenenbaum
arXiv:2609.36940v1 Announce Type: new
Abstract: Accurate dynamic scene reconstruction is important for robotic perception, where temporally consistent representations of dynamic environments are esse...
By Thai Duy Nguyen, Haitian Zhang, Addison Lin Wang
World Action Models (WAMs) are able to leverage pretrained video generators for both world modeling and action prediction. However, directly leveraging such video generators for control raises a new challenge: how to represent actions in a suitable form that aligns with pretrained video generators while carrying enough motion cues for accurate control.