Pith. sign in

REVIEW 7 cited by

Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion

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 2111.12702 v1 pith:PDUMWDKP submitted 2021-11-24 cs.CV

Tong Wu , Liang Pan , Junzhe Zhang , Tai Wang , Ziwei Liu , Dahua Lin This is my paper
classification cs.CV
keywords distancepointchamferevaluationsimilarityclouddensitycompletion
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Chamfer Distance (CD) and Earth Mover's Distance (EMD) are two broadly adopted metrics for measuring the similarity between two point sets. However, CD is usually insensitive to mismatched local density, and EMD is usually dominated by global distribution while overlooks the fidelity of detailed structures. Besides, their unbounded value range induces a heavy influence from the outliers. These defects prevent them from providing a consistent evaluation. To tackle these problems, we propose a new similarity measure named Density-aware Chamfer Distance (DCD). It is derived from CD and benefits from several desirable properties: 1) it can detect disparity of density distributions and is thus a more intensive measure of similarity compared to CD; 2) it is stricter with detailed structures and significantly more computationally efficient than EMD; 3) the bounded value range encourages a more stable and reasonable evaluation over the whole test set. We adopt DCD to evaluate the point cloud completion task, where experimental results show that DCD pays attention to both the overall structure and local geometric details and provides a more reliable evaluation even when CD and EMD contradict each other. We can also use DCD as the training loss, which outperforms the same model trained with CD loss on all three metrics. In addition, we propose a novel point discriminator module that estimates the priority for another guided down-sampling step, and it achieves noticeable improvements under DCD together with competitive results for both CD and EMD. We hope our work could pave the way for a more comprehensive and practical point cloud similarity evaluation. Our code will be available at: https://github.com/wutong16/Density_aware_Chamfer_Distance .

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. A Multi-View High-Resolution Foot-Ankle Complex Point Cloud Dataset During Gait for Occlusion-Robust 3D Completion

    cs.CV 2025-07 conditional novelty 7.0 of 10

    FootGait3D provides graded partial-to-complete real-world point clouds of the foot-ankle complex during gait, enabling benchmarking of occlusion-robust 3D completion.

  2. FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows

    cs.CV 2026-07 conditional novelty 6.5 of 10

    A two-stage flow-matching model that seeds point-cloud generation from a generated BEV density map, using teacher-estimated point pairings to keep transport paths straight, achieves SOTA JSD/IoU on SemanticKITTI compl...

  3. BubbleSH: A Dataset of Rising Bubbles with Deformable Interfaces

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A lightweight DNS-derived dataset of deformable bubble swarms with spherical-harmonic shape descriptors enables data-driven emulators that achieve 10^4-10^5x speedup over direct simulation.

  4. Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control

    cs.RO 2025-05 conditional novelty 6.0 of 10

    3D occupancy representation with a learned 3D CNN-GNN dynamics model and MPC enables a robot to shape plasticine into letter goals in both simulation and the real world.

  5. Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption

    cs.CV 2025-07 reject novelty 5.0 of 10

    A new corrupted point cloud completion benchmark and a network with contrastive feature filtering report top scores after fine-tuning, yet exhibit unexplained catastrophic failures on two corruptions.

  6. A Computationally Aware Multi Objective Framework for Camera LiDAR Calibration

    cs.RO 2025-06 reject novelty 4.0 of 10

    A multi-objective optimization with NSGA-II trades Chamfer alignment error against computational cost for camera-LiDAR calibration, yielding a Pareto frontier.

  7. Deformable registration and generative modelling of aortic anatomies by auto-decoders and neural ODEs

    cs.CV 2025-06 conditional novelty 4.0 of 10

    AD-SVFD registers and generates aortic anatomies by conditioning neural-ODE diffeomorphisms on auto-decoder latent codes, reporting accurate and fast results on healthy aortas.

Pith tools