cs.CVNov 18, 2026

WaveView: The Novel View Is in the Noise

Authors: Kaiwen Wang, Jan-Hendrik Pauls, Yinzhe Shen, Frank Bieder, Christoph Stiller

Organizations: Karlsruhe Institute of Technology, Germany · Parallel Domain, Germany · FZI Research Center for Information Technology, Germany

Abstract

Generative novel view synthesis (NVS) employs a diffusion model to render a static or dynamic scene from a target camera view. Explicit warp methods complete a reprojection of the source with video diffusion models, and implicit methods encode the camera parameters or 3D cues. Both add inference overhead, and the generated layout often drifts from the ground truth. We present WaveView, which injects the warped source into the phase of the initial noise of a pretrained generator. The Dual-Tree Complex Wavelet Packet Transform (DT-CWPT) allows local and anisotropic phase injection. The generator is thus constrained less in disoccluded regions and along the epipolar line. WaveView keeps the architecture and adds negligible overhead. On the DL3DV benchmark, it outperforms all baselines in every overlap bin. In the hardest bin, it gains 0.84 dB PSNR on the covisible region over MetaView, which shares its generator, while running 2.1 times faster. For dynamic NVS, fine-tuning AnyView with the same noise raises its zero-shot PSNR on AnyViewBench from 11.58 to 12.35 dB.

Figures & tables

Explore similar work

CardsList
  1. WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis

    Jun 30, 2026Michael Green, Gavriel Habib, Dvir Samuel +4Novel View SynthesisGenerative Modeling

  2. GenRec: Knowing Where to Reconstruct and Where to Generate

    Aug 18, 2026Ata Çelen, Jaewoo Jung, Federico Tombari +4Novel View SynthesisMulti-View Image Synthesis

  3. FrameCrafter: Novel View Synthesis as Video Completion

    Apr 9, 2026Qi Wu, Khiem Vuong, Minsik Jeon +2Video Diffusion ModelsNovel View Synthesis