Siming Yan

Siming Yan, Yuqi Yang, Yuxiao Guo et al.

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks.

Siming Yan, Chen Song, Youkang Kong et al.

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud pre-training that learns 3D representations by leveraging pre-trained 2D networks. Different from the popular practice of predicting 2D features first and then obtaining 3D features through dimensionality lifting, our approach directly uses a 3D network for feature extraction. We train the 3D feature extraction network with the help of the novel 2D knowledge transfer loss, which enforces the 2D projections of the 3D feature to be consistent with the output of pre-trained 2D networks. To prevent the feature from discarding 3D signals, we introduce the multi-view consistency loss that additionally encourages the projected 2D feature representations to capture pixel-wise correspondences across different views. Such correspondences induce 3D geometry and effectively retain 3D features in the projected 2D features. Experimental results demonstrate that our pre-trained model can be successfully transferred to various downstream tasks, including 3D shape classification, part segmentation, 3D object detection, and semantic segmentation, achieving state-of-the-art performance.

Siming Yan, Min Bai, Weifeng Chen et al.

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning capabilities. However, the generated text often suffers from inaccurate grounding in the visual input, resulting in errors such as hallucination of nonexistent scene elements, missing significant parts of the scene, and inferring incorrect attributes of and relationships between objects. To address these issues, we introduce a novel framework, ViGoR (Visual Grounding Through Fine-Grained Reward Modeling) that utilizes fine-grained reward modeling to significantly enhance the visual grounding of LVLMs over pre-trained baselines. This improvement is efficiently achieved using much cheaper human evaluations instead of full supervisions, as well as automated methods. We show the effectiveness of our approach through a variety of evaluation methods and benchmarks. Additionally, we released our human annotation (https://github.com/amazon-science/vigor) comprising 15,440 images and generated text pairs with fine-grained evaluations to contribute to related research in the community.

Dong Zhuo, Wenzhao Zheng, Sicheng Zuo et al.

With the growing adoption of vision-language-action models and world models in autonomous driving systems, scalable image tokenization becomes crucial as the interface for the visual modality. However, most existing tokenizers are designed for monocular and 2D scenes, leading to inefficiency and inter-view inconsistency when applied to high-resolution multi-view driving scenes. To address this, we propose DriveTok, an efficient 3D driving scene tokenizer for unified multi-view reconstruction and understanding. DriveTok first obtains semantically rich visual features from vision foundation models and then transforms them into the scene tokens with 3D deformable cross-attention. For decoding, we employ a multi-view transformer to reconstruct multi-view features from the scene tokens and use multiple heads to obtain RGB, depth, and semantic reconstructions. We also add a 3D head directly on the scene tokens for 3D semantic occupancy prediction for better spatial awareness. With the multiple training objectives, DriveTok learns unified scene tokens that integrate semantic, geometric, and textural information for efficient multi-view tokenization. Extensive experiments on the widely used nuScenes dataset demonstrate that the scene tokens from DriveTok perform well on image reconstruction, semantic segmentation, depth prediction, and 3D occupancy prediction tasks.

Zhe Liu, Runhui Huang, Rui Yang et al.

Although multi-modal large language models (MLLMs) have shown strong capabilities across diverse domains, their application in generating fine-grained 3D perception and prediction outputs in autonomous driving remains underexplored. In this paper, we propose DrivePI, a novel spatial-aware 4D MLLM that serves as a unified Vision-Language-Action (VLA) framework that is also compatible with vision-action (VA) models. Our method jointly performs spatial understanding, 3D perception (i.e., 3D occupancy), prediction (i.e., occupancy flow), and planning (i.e., action outputs) in parallel through end-to-end optimization. To obtain both precise geometric information and rich visual appearance, our approach integrates point clouds, multi-view images, and language instructions within a unified MLLM architecture. We further develop a data engine to generate text-occupancy and text-flow QA pairs for 4D spatial understanding. Remarkably, with only a 0.5B Qwen2.5 model as MLLM backbone, DrivePI as a single unified model matches or exceeds both existing VLA models and specialized VA models. Specifically, compared to VLA models, DrivePI outperforms OpenDriveVLA-7B by 2.5% mean accuracy on nuScenes-QA and reduces collision rate by 70% over ORION (from 0.37% to 0.11%) on nuScenes. Against specialized VA models, DrivePI surpasses FB-OCC by 10.3 RayIoU for 3D occupancy on OpenOcc, reduces the mAVE from 0.591 to 0.509 for occupancy flow on OpenOcc, and achieves 32% lower L2 error than VAD (from 0.72m to 0.49m) for planning on nuScenes. Code will be available at https://github.com/happinesslz/DrivePI

Shuangli Du, Siming Yan, Zhenghao Shi et al.

Low-light images suffer from complex degradation, and existing enhancement methods often encode all degradation factors within a single latent space. This leads to highly entangled features and strong black-box characteristics, making the model prone to shortcut learning. To mitigate the above issues, this paper proposes a wavelet-based low-light stereo image enhancement method with feature space decoupling. Our insight comes from the following findings: (1) Wavelet transform enables the independent processing of low-frequency and high-frequency information. (2) Illumination adjustment can be achieved by adjusting the low-frequency component of a low-light image, extracted through multi-level wavelet decomposition. Thus, by using wavelet transform the feature space is decomposed into a low-frequency branch for illumination adjustment and multiple high-frequency branches for texture enhancement. Additionally, stereo low-light image enhancement can extract useful cues from another view to improve enhancement. To this end, we propose a novel high-frequency guided cross-view interaction module (HF-CIM) that operates within high-frequency branches rather than across the entire feature space, effectively extracting valuable image details from the other view. Furthermore, to enhance the high-frequency information, a detail and texture enhancement module (DTEM) is proposed based on cross-attention mechanism. The model is trained on a dataset consisting of images with uniform illumination and images with non-uniform illumination. Experimental results on both real and synthetic images indicate that our algorithm offers significant advantages in light adjustment while effectively recovering high-frequency information. The code and dataset are publicly available at: https://github.com/Cherisherr/WDCI-Net.git.

Siming Yan

With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as 3D scanners, LiDARs, and RGB-D cameras, provides rich geometric, shape, and scale information. When combined with 2D images, 3D data offers machines a comprehensive understanding of their environment, benefiting applications like autonomous driving, robotics, remote sensing, and medical treatment. This dissertation focuses on three main areas: supervised representation learning for point cloud primitive segmentation, self-supervised learning methods, and transfer learning from 2D to 3D. Our approach, which integrates pre-trained 2D models to support 3D network training, significantly improves 3D understanding without merely transforming 2D data. Extensive experiments validate the effectiveness of our methods, showcasing their potential to advance point cloud representation learning by effectively integrating 2D knowledge.

Siming Yan, Zhenpei Yang, Haoxiang Li et al.

This paper advocates the use of implicit surface representation in autoencoder-based self-supervised 3D representation learning. The most popular and accessible 3D representation, i.e., point clouds, involves discrete samples of the underlying continuous 3D surface. This discretization process introduces sampling variations on the 3D shape, making it challenging to develop transferable knowledge of the true 3D geometry. In the standard autoencoding paradigm, the encoder is compelled to encode not only the 3D geometry but also information on the specific discrete sampling of the 3D shape into the latent code. This is because the point cloud reconstructed by the decoder is considered unacceptable unless there is a perfect mapping between the original and the reconstructed point clouds. This paper introduces the Implicit AutoEncoder (IAE), a simple yet effective method that addresses the sampling variation issue by replacing the commonly-used point-cloud decoder with an implicit decoder. The implicit decoder reconstructs a continuous representation of the 3D shape, independent of the imperfections in the discrete samples. Extensive experiments demonstrate that the proposed IAE achieves state-of-the-art performance across various self-supervised learning benchmarks.

Haitao Yang, Zaiwei Zhang, Siming Yan et al.

Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task is challenging because 3D scenes exhibit diverse patterns, ranging from continuous ones, such as object sizes and the relative poses between pairs of shapes, to discrete patterns, such as occurrence and co-occurrence of objects with symmetrical relationships. This paper introduces a novel neural scene synthesis approach that can capture diverse feature patterns of 3D scenes. Our method combines the strength of both neural network-based and conventional scene synthesis approaches. We use the parametric prior distributions learned from training data, which provide uncertainties of object attributes and relative attributes, to regularize the outputs of feed-forward neural models. Moreover, instead of merely predicting a scene layout, our approach predicts an over-complete set of attributes. This methodology allows us to utilize the underlying consistency constraints among the predicted attributes to prune infeasible predictions. Experimental results show that our approach outperforms existing methods considerably. The generated 3D scenes interpolate the training data faithfully while preserving both continuous and discrete feature patterns.

Siming Yan, Zhenpei Yang, Chongyang Ma et al.

This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points of different primitives. Unlike utilizing a single feature representation, HPNet leverages hybrid representations that combine one learned semantic descriptor, two spectral descriptors derived from predicted geometric parameters, as well as an adjacency matrix that encodes sharp edges. Moreover, instead of merely concatenating the descriptors, HPNet optimally combines hybrid representations by learning combination weights. This weighting module builds on the entropy of input features. The output primitive segmentation is obtained from a mean-shift clustering module. Experimental results on benchmark datasets ANSI and ABCParts show that HPNet leads to significant performance gains from baseline approaches.

Zhenpei Yang, Siming Yan, Qixing Huang

In this paper, we introduce a novel RGB-D based relative pose estimation approach that is suitable for small-overlapping or non-overlapping scans and can output multiple relative poses. Our method performs scene completion and matches the completed scans. However, instead of using a fixed representation for completion, the key idea is to utilize hybrid representations that combine 360-image, 2D image-based layout, and planar patches. This approach offers adaptively feature representations for relative pose estimation. Besides, we introduce a global-2-local matching procedure, which utilizes initial relative poses obtained during the global phase to detect and then integrate geometric relations for pose refinement. Experimental results justify the potential of this approach across a wide range of benchmark datasets. For example, on ScanNet, the rotation translation errors of the top-1/top-5 predictions of our approach are 28.6/0.90m and 16.8/0.76m, respectively. Our approach also considerably boosts the performance of multi-scan reconstruction in few-view reconstruction settings.

Siming Yan, Xuyang Fang, Bowen Xiao et al.

The abundant recurrent horizontal and feedback connections in the primate visual cortex are thought to play an important role in bringing global and semantic contextual information to early visual areas during perceptual inference, helping to resolve local ambiguity and fill in missing details. In this study, we find that introducing feedback loops and horizontal recurrent connections to a deep convolution neural network (VGG16) allows the network to become more robust against noise and occlusion during inference, even in the initial feedforward pass. This suggests that recurrent feedback and contextual modulation transform the feedforward representations of the network in a meaningful and interesting way. We study the population codes of neurons in the network, before and after learning with feedback, and find that learning with feedback yielded an increase in discriminability (measured by d-prime) between the different object classes in the population codes of the neurons in the feedforward path, even at the earliest layer that receives feedback. We find that recurrent feedback, by injecting top-down semantic meaning to the population activities, helps the network learn better feedforward paths to robustly map noisy image patches to the latent representations corresponding to important visual concepts of each object class, resulting in greater robustness of the network against noises and occlusion as well as better fine-grained recognition.

Siming Yan, Feng Shi, Yuhua Chen et al.

Coronary calcium causes beam hardening and blooming artifacts on cardiac computed tomography angiography (CTA) images, which lead to overestimation of lumen stenosis and reduction of diagnostic specificity. To properly remove coronary calcification and restore arterial lumen precisely, we propose a machine learning-based method with a multi-step inpainting process. We developed a new network configuration, Dense-Unet, to achieve optimal performance with low computational cost. Results after the calcium removal process were validated by comparing with gold-standard X-ray angiography. Our results demonstrated that removing coronary calcification from images with the proposed approach was feasible, and may potentially improve the diagnostic accuracy of CTA.