Existing 3D scene understanding tasks have achieved high performance on close-set benchmarks but fail to handle novel categories in real-world applications. To this end, we propose a Regional Point-Language Contrastive learning framework, namely RegionPLC, for open-world 3D scene understanding, which equips models trained on closed-set datasets with open-vocabulary recognition capabilities. We propose dense visual prompts to elicit region-level visual-language knowledge from 2D foundation models via captioning, which further allows us to build dense regional point-language associations. Then, we design a point-discriminative contrastive learning objective to enable point-independent learning from captions for dense scene understanding. We conduct extensive experiments on ScanNet, ScanNet200, and nuScenes datasets. Our RegionPLC significantly outperforms previous base-annotated 3D open-world scene understanding approaches by an average of 11.6\% and 6.6\% for semantic and instance segmentation, respectively. It also shows promising open-world results in absence of any human annotation with low training and inference costs. Code will be released.
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined training for 3D foreground/background segmentation, cylindrical object proposals, and point completion. Furthermore, they often overlook the inter-object feature relation that is particularly informative to hard samples for 3D annotation. To this end, we propose a simple yet effective end-to-end Context-Aware Transformer (CAT) as an automated 3D-box labeler to generate precise 3D box annotations from 2D boxes, trained with a small number of human annotations. We adopt the general encoder-decoder architecture, where the CAT encoder consists of an intra-object encoder (local) and an inter-object encoder (global), performing self-attention along the sequence and batch dimensions, respectively. The former models intra-object interactions among points, and the latter extracts feature relations among different objects, thus boosting scene-level understanding. Via local and global encoders, CAT can generate high-quality 3D box annotations with a streamlined workflow, allowing it to outperform existing state-of-the-art by up to 1.79% 3D AP on the hard task of the KITTI test set.
3D scene understanding, e.g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose ``One Thing One Click,'' meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate the per-category prototype to enhance the pseudo label quality and guide the iterative training. Besides, our model can be compatible to 3D instance segmentation equipped with a point-clustering strategy. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic and instance segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts. Codes and models are available at https://github.com/liuzhengzhe/One-Thing-One-Click.
In this paper, we present a new text-guided 3D shape generation approach (ISS++) that uses images as a stepping stone to bridge the gap between text and shape modalities for generating 3D shapes without requiring paired text and 3D data. The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between rendered images and the input text. Besides, to extend beyond the generative capability of the SVR model, we design a text-guided 3D shape stylization module that can enhance the output shapes with novel structures and textures. Further, we exploit pre-trained text-to-image diffusion models to enhance the generative diversity, fidelity, and stylization capability. Our approach is generic, flexible, and scalable, and it can be easily integrated with various SVR models to expand the generative space and improve the generative fidelity. Extensive experimental results demonstrate that our approach outperforms the state-of-the-art methods in terms of generative quality and consistency with the input text. Codes and models are released at https://github.com/liuzhengzhe/ISS-Image-as-Stepping-Stone-for-Text-Guided-3D-Shape-Generation.
Category-level 6D pose estimation aims to predict the poses and sizes of unseen objects from a specific category. Thanks to prior deformation, which explicitly adapts a category-specific 3D prior (i.e., a 3D template) to a given object instance, prior-based methods attained great success and have become a major research stream. However, obtaining category-specific priors requires collecting a large amount of 3D models, which is labor-consuming and often not accessible in practice. This motivates us to investigate whether priors are necessary to make prior-based methods effective. Our empirical study shows that the 3D prior itself is not the credit to the high performance. The keypoint actually is the explicit deformation process, which aligns camera and world coordinates supervised by world-space 3D models (also called canonical space). Inspired by these observation, we introduce a simple prior-free implicit space transformation network, namely IST-Net, to transform camera-space features to world-space counterparts and build correspondence between them in an implicit manner without relying on 3D priors. Besides, we design camera- and world-space enhancers to enrich the features with pose-sensitive information and geometrical constraints, respectively. Albeit simple, IST-Net becomes the first prior-free method that achieves state-of-the-art performance, with top inference speed on the REAL275 dataset. Our code and models will be publicly available.
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream literature where the efficacy of strong backbones and effective decoder heads has been well studied, in this paper, additional contextual hints are instead exploited via learning a context-aware classifier whose content is data-conditioned, decently adapting to different latent distributions. Since only the classifier is dynamically altered, our method is model-agnostic and can be easily applied to generic segmentation models. Notably, with only negligible additional parameters and +2\% inference time, decent performance gain has been achieved on both small and large models with challenging benchmarks, manifesting substantial practical merits brought by our simple yet effective method. The implementation is available at \url{https://github.com/tianzhuotao/CAC}.
3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and efficient framework, with no need for sparse-to-dense conversion or NMS post-processing. Our method achieves a better speed-accuracy trade-off than other mainframe detectors on the nuScenes dataset. For the first time, we show that a fully sparse voxel-based representation works decently for LIDAR 3D object detection and tracking. Extensive experiments on nuScenes, Waymo, and Argoverse2 benchmarks validate the effectiveness of our approach. Without bells and whistles, our model outperforms all existing LIDAR methods on the nuScenes tracking test benchmark.
Implicit neural rendering, which uses signed distance function (SDF) representation with geometric priors (such as depth or surface normal), has led to impressive progress in the surface reconstruction of large-scale scenes. However, applying this method to reconstruct a room-level scene from images may miss structures in low-intensity areas or small and thin objects. We conducted experiments on three datasets to identify limitations of the original color rendering loss and priors-embedded SDF scene representation. We found that the color rendering loss results in optimization bias against low-intensity areas, causing gradient vanishing and leaving these areas unoptimized. To address this issue, we propose a feature-based color rendering loss that utilizes non-zero feature values to bring back optimization signals. Additionally, the SDF representation can be influenced by objects along a ray path, disrupting the monotonic change of SDF values when a single object is present. To counteract this, we explore using the occupancy representation, which encodes each point separately and is unaffected by objects along a querying ray. Our experimental results demonstrate that the joint forces of the feature-based rendering loss and Occ-SDF hybrid representation scheme can provide high-quality reconstruction results, especially in challenging room-level scenarios. The code would be released.
A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.
Although considerable progress has been obtained in neural network quantization for efficient inference, existing methods are not scalable to heterogeneous devices as one dedicated model needs to be trained, transmitted, and stored for one specific hardware setting, incurring considerable costs in model training and maintenance. In this paper, we study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. With this representation, we can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model. To this end, we propose a simple once quantization-aware training (QAT) scheme for obtaining high-performance vertical-layered models. Our design incorporates a cascade downsampling mechanism which allows us to obtain multiple quantized networks from one full precision source model by progressively mapping the higher precision weights to their adjacent lower precision counterparts. Then, with networks of different bit-widths from one source model, multi-objective optimization is employed to train the shared source model weights such that they can be updated simultaneously, considering the performance of all networks. By doing this, the shared weights will be optimized to balance the performance of different quantized models, thus making the weights transferable among different bit widths. Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width. Code will be available.