arXiv Computer Vision
Distortion-Aware Spatiotemporal Learning for Real-Time Wide-Angle Video Rectification
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 1
Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts
arXiv:2512.18718v3 Announce Type: replace Abstract: Image correction and rectangling are valuable tasks in practical photography systems such as smartphones. Recent remarkable advancements in deep le...
arXiv Computer Vision
Oct 9
TKCAM: Text and Keyframe to Camera Trajectory Generation
TKCAM is a new framework for generating controllable camera motion conditioned on text and sparse keyframes, using a 12‑dimensional kinematic representation and a two‑stage masked transformer with residual vector quantization. It allows users to provide free‑form text prompts and RGB observations at selected timestamps, enabling temporally localized visual guidance for coherent trajectory synthesis. The authors also introduce the RealEstate10K‑Cap dataset and a Universal CLaTr Evaluator, showing that TKCAM outperforms recent baselines on FID, text‑motion matching, and retrieval metrics.
Hugging Face Trending Papers
Oct 8
TKCAM: Text and Keyframe to Camera Trajectory Generation
Generating high-quality and controllable camera motion is essential for AI-assisted cinematography, video synthesis, and 3D scene understanding. We introduce TKCAM, a Text- and Keyframe-conditioned CA...
arXiv Computer Vision
Sep 7
Temporal Residual Neural Radiance Fields for Monocular Video Dynamic Human Body Reconstruction
The paper introduces Temporal Residual Neural Radiance Fields for reconstructing dynamic human bodies from monocular video. It builds a temporal residual field independent of MLPs, reduces trainable parameters, speeds up rendering, and employs a multi‑dimensional loss to improve pixel‑level accuracy. Experiments show higher PSNR and SSIM than recent methods while being roughly 780 times faster than Anim‑NeRF and Neural Body.
arXiv Computer Vision
Oct 2
MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
arXiv:2605.30320v2 Announce Type: replace Abstract: Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D...
arXiv Computer Vision
Oct 27
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
arXiv:2605.23889v2 Announce Type: replace Abstract: Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods of...