REVIEW 6 cited by
Point Transformer V3: Simpler, Faster, Stronger
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
read the original abstract
This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing, leveraging the power of scale. Drawing inspiration from recent advances in 3D large-scale representation learning, we recognize that model performance is more influenced by scale than by intricate design. Therefore, we present Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the overall performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns. This principle enables significant scaling, expanding the receptive field from 16 to 1024 points while remaining efficient (a 3x increase in processing speed and a 10x improvement in memory efficiency compared with its predecessor, PTv2). PTv3 attains state-of-the-art results on over 20 downstream tasks that span both indoor and outdoor scenarios. Further enhanced with multi-dataset joint training, PTv3 pushes these results to a higher level.
Forward citations
Cited by 6 Pith papers
-
Proteus: A Truncation-Robust Entropy Model for Progressive LiDAR Compression
A LiDAR codec that keeps the most significant range bits in a self-contained stream and encodes the rest in a FIFO stream, making any prefix of the truncatable stream decode to a deterministically coarser point cloud.
-
GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
A causal transformer with 3D RoPE generates vector-quantized 3D Gaussian latent grids autoregressively, enabling unconditional synthesis, completion, and open-ended outpainting of indoor scenes.
-
Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views
Point-PQAE pre-trains point cloud transformers by cross-reconstructing one randomly cropped and rotated view from another, improving frozen-feature accuracy on ScanObjectNN by up to 7% over Point-MAE.
-
Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning
AsymDSD unifies latent masked point modeling and cross-view invariance self-distillation to learn 3D representations, reporting 90.53% on ScanObjectNN and 93.72% with 930k-shape pretraining.
-
Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation
A weakly supervised 3D point cloud segmentation method that back-projects Semantic-SAM 2D masks into 3D, propagates sparse labels inside masks, and uses reliability-filtered pseudo labels, reporting state-of-the-art m...
-
Technical Report for ICRA 2025 GOOSE 3D Semantic Segmentation Challenge: Adaptive Point Cloud Understanding for Heterogeneous Robotic Systems
Applying Point Prompt Tuning with platform-specific conditioning to a PTv3 backbone improves multi-platform LiDAR segmentation on GOOSE/GOOSE-Ex validation data, with mIoU gains up to 22.59% relative to the PTv3 baseline.
Discussion (0). Sign in to comment.