GenRec is introduced, a multi-view flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow, and attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones.
Abstract
Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a multi-view flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow. Guided by an observation mask derived from the source cameras and a monocular depth estimator, a flow matching backbone jointly denoises RGB and scene-coordinate maps across all target views, while a pixel-space refinement stage restores high-frequency detail on observed pixels; the same mask gates supervision so regression signals do not contaminate the generative prior. Across RealEstate10K, DL3DV-10K, and Mip-NeRF~360, in both single-view extrapolation and two-view interpolation, GenRec attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones, showing the effectiveness of our approach.
Novel view synthesis from sparse inputs requires both geometric grounding from the observed views and generative priors of unobserved regions, motivating recent hybrid methods that combine reconstruction and generation. However, existing methods bridge the two with rendered images or explicit 3D representations such as point maps or 3D Gaussians. Generation is thus conditioned on a lossy and imperfect projection of the scene, inheriting its errors, and reconstruction receives no signal from generation to correct them. We present RoGe, an end-to-end unified reconstruction and generation framework that removes this explicit bridge. It targets roaming within a scene anchored by sparse views: given a few posed images and a camera trajectory, it synthesizes a temporally coherent video along that trajectory. From the sparse input views, RoGe builds an implicit scene representation with a feed-forward reconstruction model, and queries it with target camera rays to obtain per-view geometric features. These features are injected into a video diffusion model as conditioning, without any 3D intermediate. Both modules are trained jointly, so the generation objective directly shapes its own geometric conditioning. We conduct experiments on DL3DV, where RoGe outperforms reconstruction-based, generation-based, and hybrid baselines on image-level metrics and video-level temporal consistency. Ablations confirm that ray-queried implicit features outperform both raw reconstruction tokens and rendered RGB as conditioning, and that joint training brings further gains. Our project page is at https://jerry-locker.github.io/roge/.
Xiaolei Lang, Ze Kang, Zehao Huang et al.· 0 citations
Direct latent-to-4D generation is introduced and instantiate it as Latent-to-4D, which bypasses RGB by aligning a video latent with the token grid of a pretrained 4D decoder and refining it through frame-wise and global spatiotemporal attention.
Image relighting is traditionally tackled via complex inverse rendering pipelines, which suffer from ill-posed optimization, or single-image generative models that ignore crucial multi-view cues necessary for understanding 3D geometry and material interactions. To address these limitations, we introduce a feed-forward generative Transformer for direct single- and multi-view image relighting that entirely bypasses explicit intrinsic property estimation. Adapted from a video foundation model, our architecture features a latent illumination module that dynamically injects target environment maps into spatial features via cross-attention. Furthermore, we employ permutation-invariant positional encodings to symmetrically process unordered multi-view inputs without sequential bias. To train this robust data-driven model, we construct the massive Laval Objaverse Dataset (LOD), comprising 90K objects and 39K unique illuminations. Extensive experiments demonstrate state-of-the-art visual quality, photorealistic relighting quality, and strong zero-shot generalization across single-view, multi-view, and novel-view relighting tasks.
Hejun Wang, Jinxi Li, Junwei Jiang et al.· 0 citations
UniWorld-View is introduced, a unified framework for controllable large-baseline novel view synthesis from monocular inputs that integrates explicit 3D guidance with generative diffusion modeling to enable precise camera control and geometrically consistent view generation.
Haiyang Zhou, Wangbo Yu, Chaoran Feng et al.· 1 citation
SpatialCrafter is presented, a novel two-stage framework that addresses explorable image-to-scene generation issues by introducing a global 3D proxy for high-fidelity image-to-scene generation and appearance refinement and introduces Parallel Geometry Injection and Proxy-Aware Corruption training strategies.
Chuan Fang, Lingteng Qiu, Yixun Liang et al.· 0 citations
DiGS-Avatar is proposed, which reformulates this task as an efficient, diffusion-based UV-latent completion task, ensuring 3D consistency by design, and introduces a teacher-student framework where a multi-view teacher provides geometrically aligned pseudo-ground-truth latents to supervise a single-view diffusion student.
Jiakun Li, Li Fang, Hao Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
