REVIEW 10 cited by
RayZer: A Self-supervised Large View Synthesis Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
RayZer: A Self-supervised Large View Synthesis Model
read the original abstract
We present RayZer, a self-supervised multi-view 3D Vision model trained without any 3D supervision, i.e., camera poses and scene geometry, while exhibiting emerging 3D awareness. Concretely, RayZer takes unposed and uncalibrated images as input, recovers camera parameters, reconstructs a scene representation, and synthesizes novel views. During training, RayZer relies solely on its self-predicted camera poses to render target views, eliminating the need for any ground-truth camera annotations and allowing RayZer to be trained with 2D image supervision. The emerging 3D awareness of RayZer is attributed to two key factors. First, we design a self-supervised framework, which achieves 3D-aware auto-encoding of input images by disentangling camera and scene representations. Second, we design a transformer-based model in which the only 3D prior is the ray structure, connecting camera, pixel, and scene simultaneously. RayZer demonstrates comparable or even superior novel view synthesis performance than ``oracle'' methods that rely on pose annotations in both training and testing. Project: https://hwjiang1510.github.io/RayZer/
Forward citations
Cited by 10 Pith papers
-
WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis
WarpHammer densifies scene warps with 3D object priors from generative models and fuses pose-unknown auxiliary views via multi-view geometry to enable stable extreme novel view synthesis.
-
Track-Leakage-Free Hold-Out Self-Validation for Photogrammetric Reconstruction: Protocol, Sensitivity, and Limits
A track-leakage-free hold-out self-consistency score saturates at 1.00 while true reconstruction error swings up to 106 m, proving internal consistency is not absolute accuracy.
-
Track-Leakage-Free Hold-Out Self-Validation for Photogrammetric Reconstruction: Protocol, Sensitivity, and Limits
A track-leakage-free hold-out self-check for SfM is well-posed but only detects fragmentation; it cannot measure absolute accuracy, staying pinned at confidence 1.00 on models that are 55–106 m wrong.
-
Lighting-Consistent Object Transfer Across Radiance Fields
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
-
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
Decouples semantic and spatial tokens in NVS transformers to resolve representation ambiguity, yielding consistent gains with near-zero added latency.
-
Self-Improving 4D Perception via Self-Distillation
SelfEvo enables pretrained 4D perception models to self-improve on unlabeled videos via self-distillation, delivering up to 36.5% relative gains in video depth estimation and 20.1% in camera estimation across eight be...
-
ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstruction
ILV recovers fine anatomical detail in sparse-view CBCT by iteratively updating an explicit 3D latent volume with multi-view X-ray features and a learned prior, outperforming prior feed-forward and optimization method...
-
Multi-view Pyramid Transformer: Look Coarser to See Broader
MVP uses a two-level hierarchy of attention windows and token resolutions to reconstruct large 3D scenes from up to 256 input views in a single feed-forward pass, beating Long-LRM and iLRM on DL3DV and several zero-sh...
-
OmniNWM: Omniscient Driving Navigation World Models
OmniNWM jointly generates long panoramic multi-modal driving videos, controls them precisely via normalized Plücker ray-maps, and derives dense driving rewards from generated 3D occupancy.
-
Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
UniSplat learns consistent 3D geometry, appearance, and semantics from unposed images using dual masking, progressive Gaussian splatting, and recalibration to align predictions across tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.