paper-with-me

Papers

FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow

2026-09-03 · Byeongjun Park, Byung-Hoon Kim, Hyungjin Chung hf

We present FlashRender, a few-step generative rendering framework that retakes a source video along a target camera trajectory in seconds. We identify sampling-step-dependent camera control as a prominent manifestation of discretization error in existing multi-step generative rendering models and show that resolving this inconsistency substantially lowers denoising trajectory curvature, facilitating subsequent step distillation. To this end, we introduce Representation Transformation and Alignment (RETA), which aligns hidden source-video representations with target-video features from a frozen visual geometry model. This directly encodes the geometric transformation within the source-video stream, enabling sampling-step-consistent camera control. We then fine-tune the model with the MeanFlow objective on the lower-curvature denoising trajectory induced by RETA, allowing the model to more effectively address discretization error. Finally, we apply on-policy flow map distillation to correct self-rollout errors under fixed few-step sampling. Extensive experiments show that RETA, MeanFlow, and on-policy flow map distillation play complementary roles in few-step generative rendering. Together, they enable our approach to match multi-step baselines in video quality and geometric consistency at 25x lower sampling cost while achieving superior camera controllability, even under out-of-distribution target camera trajectories.

📄 PDF Abstract BibTeX arXiv:2609.03563

Code (2)

Tavish9/awesome-daily-AI-arxiv ★ 114
Valiant-Cat/hfpaper

Similar Papers 제목 키워드 기반

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

2025-03-14 · Jianhong Bai, Menghan Xia, Xiao Fu, Xintao Wang 외

Camera control has been actively studied in text or image conditioned video generation tasks. However, altering camera trajectories of a given video remains under-explored, despite its importance in the field of video cr…

Super-ResolutionVideo GenerationVideo Stabilization

Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering

2026-01-14 · Jieying Chen, Jeffrey Hu, Joan Lasenby, Ayush Tewari arxiv

Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency …

3D ReconstructionVideo Generation

Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

2025-06-16 · Junyoung Seo, Jisang Han, Jaewoo Jung, Siyoon Jin 외

We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the…

Novel View Synthesis

ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories

2025-12-03 · Yaokun Li, Shuaixian Wang, Mantang Guo, Jiehui Huang 외 arxiv

Synthesizing multi-pass videos is important for autonomous driving. While current repair-based methods often struggle with out-of-distribution artifacts, camera-controlled methods often produce 3D-inconsistent results du…

Video Generation

Plenoptic Video Generation

2026-01-08 · Xiao Fu, Shitao Tang, Min Shi, Xian Liu 외 arxiv

Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency a…

Video GenerationVideo Retrieval