Pith. sign in

REVIEW 23 cited by

PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting

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

arxiv 2410.22128 v2 pith:FY5VQ7CR submitted 2024-10-29 cs.CV

classification cs.CV
keywords gaussianpf3platsynthesisviewachieveacrossalignmentsassumptions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We consider the problem of novel view synthesis from unposed images in a single feed-forward. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS, where we further extend it to offer a practical solution that relaxes common assumptions such as dense image views, accurate camera poses, and substantial image overlaps. We achieve this through identifying and addressing unique challenges arising from the use of pixel-aligned 3DGS: misaligned 3D Gaussians across different views induce noisy or sparse gradients that destabilize training and hinder convergence, especially when above assumptions are not met. To mitigate this, we employ pre-trained monocular depth estimation and visual correspondence models to achieve coarse alignments of 3D Gaussians. We then introduce lightweight, learnable modules to refine depth and pose estimates from the coarse alignments, improving the quality of 3D reconstruction and novel view synthesis. Furthermore, the refined estimates are leveraged to estimate geometry confidence scores, which assess the reliability of 3D Gaussian centers and condition the prediction of Gaussian parameters accordingly. Extensive evaluations on large-scale real-world datasets demonstrate that PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices. project page: https://cvlab-kaist.github.io/PF3plat/

Discussion (0). Sign in to comment.

Forward citations

Cited by 23 Pith papers

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

  1. ZipSplat: Fewer Gaussians, Better Splats

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    ZipSplat uses multi-view token extraction followed by k-means clustering and attention to decode compact scene tokens into unconstrained 3D Gaussians, achieving SOTA pose-free results with ~6x fewer primitives.

  2. Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    C4G introduces compact timestamp-conditioned Gaussian query tokens that aggregate full temporal context to decode 3D Gaussians with timestamp-modulated positions for feed-forward 4D reconstruction from monocular video...

  3. GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.

  4. No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.

  5. VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    VGGT-Edit proposes a native 3D text-conditioned editing framework using depth-synchronized injection and residual field prediction, plus the DeltaScene dataset, outperforming 2D-lifting methods.

  6. ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.

  7. SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    SplatWeaver dynamically allocates Gaussian primitives via cardinality experts and pixel-level routing guided by high-frequency cues for improved generalizable novel view synthesis.

  8. SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    SplatWeaver uses cardinality Gaussian experts and pixel-level routing to dynamically allocate varying numbers of Gaussian primitives for generalizable novel view synthesis.

  9. TORA: Topological Representation Alignment for 3D Shape Assembly

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    TORA distills topological structure from pretrained 3D encoders into flow-matching backbones via cosine matching and CKA loss, delivering up to 6.9x faster convergence and better accuracy on 3D shape assembly benchmar...

  10. GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A dual-stream feed-forward 3DGS codec plus geometry-guided one-step diffusion decoding beats cascaded compressors on rate-distortion while keeping multi-view consistency.

  11. NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Anchoring Gaussian centers to predicted raymaps and jointly optimizing RGB, raymap, and camera losses with a dual-frequency curriculum suppresses pose drift and improves pose-free 3D reconstruction on long sequences.

  12. OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    FreeStreamGS achieves online NVS from unposed streaming inputs competitive with offline 3DGS methods via decoupled intrinsic recovery and dynamic point refinement.

  13. OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images

    cs.CV 2026-06 conditional novelty 6.0 of 10

    An online feed-forward 3D Gaussian Splatting method stabilizes causal reconstruction with first-frame-anchored focal recovery and per-pixel 3D offsets, matching offline sparse-view baselines.

  14. RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    RayDer is a unified transformer backbone for self-supervised static-scene novel view synthesis that absorbs dynamic content as a nuisance factor and shows power-law scaling with data and compute while matching supervi...

  15. Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    A feed-forward model aligns ground and satellite features to predict Gaussian splats for improved novel-view synthesis on georeferenced outdoor scenes.

  16. EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    EnerGS introduces an energy-based soft guidance mechanism for partial geometry in 3D Gaussian Splatting to improve reconstruction quality and reduce overfitting in sparse outdoor settings.

  17. Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temp...

  18. C3G: Learning Compact 3D Representations with 2K Gaussians

    cs.CV 2025-12 unverdicted novelty 6.0 of 10

    C3G creates compact 3D Gaussian representations with 2K points by guiding placement via learnable tokens that aggregate multi-view features through attention, yielding better efficiency and performance than dense methods.

  19. iLRM: An Iterative Large 3D Reconstruction Model

    cs.CV 2025-07 conditional novelty 6.0 of 10

    iLRM reconstructs 3D Gaussian scenes from multiple photos through iterative refinement of viewpoint tokens, achieving higher quality and speed than prior feed-forward models.

  20. ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion

    cs.CV 2026-07 conditional novelty 5.0 of 10

    ATSplat reconstructs 3D scenes from multiple photos in a single forward pass with ~5.7× fewer Gaussians than dense feed-forward 3DGS and comparable or better rendering quality.

  21. NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Anchoring 3D Gaussian centers to ray-map predictions and jointly optimizing geometry with appearance supervision suppresses pose drift in unposed feed-forward 3D reconstruction.

  22. TORA: Topological Representation Alignment for 3D Shape Assembly

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    Aligning flow-matching assembly networks to frozen 3D encoder topology via cosine and CKA losses speeds training up to 6.9× and improves in- and out-of-distribution assembly accuracy with zero inference cost.

  23. DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A pose-free deblurring 3D Gaussian Splatting pipeline using DUSt3R point clouds, confidence-balanced sampling, and event-decoded latent image supervision.

Pith tools