DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis

• URL: http://arxiv.org/abs/2605.16937v1
• Date: Sat, 16 May 2026 11:14:18 GMT
• Title: DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis
• Abstract summary: Trajectory-controlled video generation has become essential for controllable video generation.<n>Existing solutions for extreme-view synthesis typically require dedicated video pairs, demanding substantial annotation effort.<n>We propose Dynamic Extreme VIew Synthesis-GRPO, a GRPO-based framework for trajectory-controlled video generation.
• Score: 54.19006030081092
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Trajectory-controlled video generation has become essential for controllable video generation. While current methods perform well under small-view camera motions, they degrade significantly with large-view motions. Existing solutions for extreme-view synthesis typically require dedicated video pairs, demanding substantial annotation effort. To address these limitations, we propose Dynamic Extreme VIew Synthesis-GRPO (DEVIS-GRPO), a GRPO-based framework for trajectory-controlled video generation, the first online policy gradient method for extreme view video generation. Central to our approach is a novel sampling strategy: Accumulative Dynamic Extreme VIew Synthesis (ADEVIS), which achieves large-view camera motions by progressively accumulating small-view increments. This method delivers two key advantages: 1) enhanced training efficiency, as it eliminates the need to warm-start the policy model by collecting expensive paired large-view videos, and 2) increased sampling diversity, achieved by flexibly varying trajectory configurations. Finally, we designed a multi-level consistency-quality reward function to select high-quality samples for model optimization. Experiments on the Kubric-4D, iPhone, and DL3DV datasets demonstrate our method's superiority. On Kubric-4D, we achieve relative improvements of 21.57% in PSNR and 7.31% in SSIM over the second-best method in non-occlusion areas. On iPhone, LPIPS is reduced by 18.56%.

Related papers

• SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection [61.05420454815012]
  AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones.<n>In practice, detectors trained on existing data often fail to generalize to newly emerging generative models.<n>We propose SphereVideo, a novel framework for AIGV detection built on two key observations.
  arXiv  Detail & Related papers  (2026-08-02T15:54:54Z)
• HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video [58.85548854304172]
  HiReFF is a feed-forward method for 2K-resolution 360 human video reconstruction from uncalibrated sparse-view videos.<n>Our framework decomposes the problem into two key tasks: 3D Gaussian reconstruction from sparse-view videos and computationally efficient high-resolution synthesis.<n> Experiments demonstrate that HiReFF significantly outperforms existing methods in high-resolution streaming video reconstruction.
  arXiv  Detail & Related papers  (2026-06-28T11:01:36Z)
• TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment [28.18756041538092]
  We present TAGRPO, a robust framework for I2V models inspired by contrastive learning.<n>Our approach is grounded in the observation that rollout videos generated from identical initial noise provide superior guidance for optimization.
  arXiv  Detail & Related papers  (2026-01-09T11:15:27Z)
• Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation [19.119239411510936]
  We introduce a GT-Pair that builds high-quality preference pairs by using real videos as positives and model-generated videos as negatives.<n>We also present Reg-DPO, which incorporates the SFT loss as a regularization term into the DPO loss to enhance training stability and generation fidelity.
  arXiv  Detail & Related papers  (2025-11-03T11:04:22Z)
• SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution [46.311223206965934]
  We study key design principles for latter cascaded video super-resolution models, which are underexplored currently.<n>First, we propose two strategies to generate training pairs that better mimic the output characteristics of the base model, ensuring alignment between the VSR model and its upstream generator.<n>Second, we provide critical insights into VSR model behavior through systematic analysis of (1) timestep sampling strategies, (2) noise augmentation effects on low-resolution (LR) inputs.
  arXiv  Detail & Related papers  (2025-06-24T17:57:26Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• HuViDPO:Enhancing Video Generation through Direct Preference Optimization for Human-Centric Alignment [13.320911720001277]
  We introduce the strategy of Direct Preference Optimization (DPO) into text-to-video (T2V) tasks.<n>Existing T2V generation methods lack a well-formed pipeline with exact loss function to guide the alignment of generated videos with human preferences.
  arXiv  Detail & Related papers  (2025-02-02T16:55:42Z)
• Improving Video Generation with Human Feedback [105.81833319891537]
  We develop a systematic pipeline that harnesses human feedback to mitigate video generation problems.<n>We introduce VideoReward, a multi-dimensional video reward model, and examine how annotations and various design choices impact its rewarding efficacy.
  arXiv  Detail & Related papers  (2025-01-23T18:55:41Z)
• ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler [53.98558445900626]
  Current image-to-video diffusion models, while powerful in generating videos from a single frame, need adaptation for two-frame conditioned generation.<n>We introduce a novel, bidirectional sampling strategy to address these off-manifold issues without requiring extensive re-noising or fine-tuning.<n>Our method employs sequential sampling along both forward and backward paths, conditioned on the start and end frames, respectively, ensuring more coherent and on-manifold generation of intermediate frames.
  arXiv  Detail & Related papers  (2024-10-08T03:01:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.