FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors

• URL: http://arxiv.org/abs/2608.23549v1
• Date: Mon, 24 Aug 2026 17:51:33 GMT
• Title: FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
• Abstract summary: We present FixAnything, a model for fixing a wide range of rendering artifacts.<n>It does so by repurposing a pretrained video generative model, leveraging its implicit multi-view priors with only minimal modification.<n>Our key insight is that even noisily-rendered sequences preserve camera motion and coarse scene structure, allowing cleanup to be formulated as video-to-video translation.
• Score: 46.96412859785915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces artifacts when input views are sparse or target views lie far from the input. Recent work mitigates these artifacts using diffusion-based generative priors, but is specialized to individual representations and require custom architectures or extensive retraining. We present FixAnything, a single model for fixing a wide range of rendering artifacts. It does so by repurposing a pretrained video generative model, leveraging its implicit multi-view priors with only minimal modification and lightweight finetuning. Our key insight is that even noisily-rendered sequences preserve camera motion and coarse scene structure, allowing cleanup to be formulated as video-to-video translation. To control what scene structure should be preserved, we introduce a binary mask denoting the clean pixels, enabling the model to anchor its output to high-quality inputs (e.g. training views) while refining the rest. To encourage FixAnything to produce 3D-consistent renderings that support downstream reconstruction, we use camera pose accuracy (recovered via structure-from-motion) as a reward signal for direct preference optimization (DPO). Across four distinct 3D representations, FixAnything consistently improves rendering quality with lightweight finetuning, demonstrating that a single generalist video prior can replace multiple specialist refinement pipelines. The simplicity of the framework enables immediate adoption of stronger future video models without architectural redesign.

Related papers

• Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images [27.013348160823828]
  We introduce a training-free system for reconstructing, understanding, and rendering 3D indoor scenes from a sparse set of unposed RGB images.<n>Unlike traditional radiance field approaches that require dense views and per-scene optimization, our pipeline achieves high-fidelity results without any training or pose preprocessing.
  arXiv  Detail & Related papers  (2026-03-22T10:56:15Z)
• TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos [65.99602532894241]
  We introduce TAPESTRY, a framework for generating high-fidelity TTVs conditioned on explicit 3D geometry.<n>We also design a method for downstream reconstruction tasks from the TTV input, featuring a multi-stage pipeline with 3D-Aware Inpainting.<n>Results demonstrate that our method outperforms existing approaches in both video consistency and final reconstruction quality.
  arXiv  Detail & Related papers  (2026-03-18T14:02:09Z)
• SViM3D: Stable Video Material Diffusion for Single Image 3D Generation [48.986972061812004]
  Video diffusion models have been successfully used to reconstruct 3D objects from a single image efficiently.<n>We extend a latent video diffusion model to output spatially varying PBR parameters and surface normals jointly with each generated view based on explicit camera control.<n>This unique setup allows for relighting and generating a 3D asset using our model as neural prior.
  arXiv  Detail & Related papers  (2025-10-09T14:29:47Z)
• Scaling Sequence-to-Sequence Generative Neural Rendering [37.23230422802279]
  Kaleido is a family of generative models designed for photorealistic, unified object- and scene-level neural rendering.<n>We introduce key architectural innovations that enable our model to:.<n>perform generative view synthesis without explicit 3D representations;.<n>generate any number of 6-DoF target views conditioned on any number of reference views;.<n> seamlessly unify 3D and video modelling within a single decoder-only rectified flow transformer.
  arXiv  Detail & Related papers  (2025-10-05T15:03:31Z)
• PS4PRO: Pixel-to-pixel Supervision for Photorealistic Rendering and Optimization [3.53658451351123]
  We propose to use video frame as the data augmentation method for neural rendering.<n>PS4PRO is trained on diverse video datasets, implicitly modeling camera movement as well as real-world 3D geometry.<n>Our results indicate that our method improves the reconstruction performance on both static and dynamic scenes.
  arXiv  Detail & Related papers  (2025-05-28T17:35:39Z)
• VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment [54.66217340264935]
  VideoLifter is a novel video-to-3D pipeline that leverages a local-to-global strategy on a fragment basis.<n>It significantly accelerates the reconstruction process, reducing training time by over 82% while holding better visual quality than current SOTA methods.
  arXiv  Detail & Related papers  (2025-01-03T18:52:36Z)
• Wonderland: Navigating 3D Scenes from a Single Image [43.99037613068823]
  We introduce a large-scale reconstruction model that leverages latents from a video diffusion model to predict 3D Gaussian Splattings of scenes in a feed-forward manner.<n>We train the 3D reconstruction model to operate on the video latent space with a progressive learning strategy, enabling the efficient generation of high-quality, wide-scope, and generic 3D scenes.
  arXiv  Detail & Related papers  (2024-12-16T18:58:17Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)
• GenDeF: Learning Generative Deformation Field for Video Generation [89.49567113452396]
  We propose to render a video by warping one static image with a generative deformation field (GenDeF) Such a pipeline enjoys three appealing advantages.
  arXiv  Detail & Related papers  (2023-12-07T18:59:41Z)
• Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives [70.32817882783608]
  We present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. Unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points.
  arXiv  Detail & Related papers  (2023-07-11T17:58:31Z)

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.