Pith. sign in

REVIEW 5 cited by

PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2411.16877 v1 pith:PVPLR5MG submitted 2024-11-25 cs.CV

Zequn Chen , Jiezhi Yang , Heng Yang This is my paper · ORCID
classification cs.CV
keywords pref3rgaussiannovel-viewsequencefeed-forwardpose-freeenablingfield
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present PreF3R, Pose-Free Feed-forward 3D Reconstruction from an image sequence of variable length. Unlike previous approaches, PreF3R removes the need for camera calibration and reconstructs the 3D Gaussian field within a canonical coordinate frame directly from a sequence of unposed images, enabling efficient novel-view rendering. We leverage DUSt3R's ability for pair-wise 3D structure reconstruction, and extend it to sequential multi-view input via a spatial memory network, eliminating the need for optimization-based global alignment. Additionally, PreF3R incorporates a dense Gaussian parameter prediction head, which enables subsequent novel-view synthesis with differentiable rasterization. This allows supervising our model with the combination of photometric loss and pointmap regression loss, enhancing both photorealism and structural accuracy. Given a sequence of ordered images, PreF3R incrementally reconstructs the 3D Gaussian field at 20 FPS, therefore enabling real-time novel-view rendering. Empirical experiments demonstrate that PreF3R is an effective solution for the challenging task of pose-free feed-forward novel-view synthesis, while also exhibiting robust generalization to unseen scenes.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation

    cs.CV 2025-06 conditional novelty 7.0 of 10

    TinySplat compresses feedforward 3D Gaussian scenes by 105-199x on two-view benchmarks (about 50x on DL3DV) while keeping rendered quality close to the uncompressed model.

  2. PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    PanoSplatt3R adapts a perspective pretrained stereo model to unposed wide-baseline panorama reconstruction with per-head rolled rotary positional embeddings, achieving SOTA on HM3D and Replica.

  3. SpatialTrackerV2: 3D Point Tracking Made Easy

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A single feed-forward model jointly estimates video depth, camera poses, and 3D point trajectories from monocular video, setting a new state of the art on TAPVid-3D.

  4. E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    E3D-Bench compares 16 3D geometric foundation models on depth, reconstruction, pose, and view-synthesis tasks with a unified evaluation toolkit.

  5. Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A survey of feed-forward 3D reconstruction models that jointly estimate camera poses and dense geometry from images in one network pass.

Pith tools