The rapid advancement of Large Multi-modal Models (LMMs) has enabled their application in scientific problem-solving, yet their fine-grained capabilities remain under-explored. In this paper, we introduce SciVerse, a multi-modal scientific evaluation benchmark to thoroughly assess LMMs across 5,735 test instances in five distinct versions. We aim to investigate three key dimensions of LMMs: scientific knowledge comprehension, multi-modal content interpretation, and Chain-of-Thought (CoT) reasoning. To unveil whether LMMs possess sufficient scientific expertise, we first transform each problem into three versions containing different levels of knowledge required for solving, i.e., Knowledge-free, -lite, and -rich. Then, to explore how LMMs interpret multi-modal scientific content, we annotate another two versions, i.e., Vision-rich and -only, marking more question information from texts to diagrams. Comparing the results of different versions, SciVerse systematically examines the professional knowledge stock and visual perception skills of LMMs in scientific domains. In addition, to rigorously assess CoT reasoning, we propose a new scientific CoT evaluation strategy, conducting a step-wise assessment on knowledge and logical errors in model outputs. Our extensive evaluation of different LMMs on SciVerse reveals critical limitations in their scientific proficiency and provides new insights into future developments. Project page: https://sciverse-cuhk.github.io

Encoder-free architectures have been preliminarily explored in the 2D visual domain, yet it remains an open question whether they can be effectively applied to 3D understanding scenarios. In this paper, we present the first comprehensive investigation into the potential of encoder-free architectures to overcome the challenges of encoder-based 3D Large Multimodal Models (LMMs). These challenges include the failure to adapt to varying point cloud resolutions and the point features from the encoder not meeting the semantic needs of Large Language Models (LLMs). We identify key aspects for 3D LMMs to remove the encoder and enable the LLM to assume the role of the 3D encoder: 1) We propose the LLM-embedded Semantic Encoding strategy in the pre-training stage, exploring the effects of various point cloud self-supervised losses. And we present the Hybrid Semantic Loss to extract high-level semantics. 2) We introduce the Hierarchical Geometry Aggregation strategy in the instruction tuning stage. This incorporates inductive bias into the LLM early layers to focus on the local details of the point clouds. To the end, we present the first Encoder-free 3D LMM, ENEL. Our 7B model rivals the current state-of-the-art model, ShapeLLM-13B, achieving 55.0%, 50.92%, and 42.7% on the classification, captioning, and VQA tasks, respectively. Our results demonstrate that the encoder-free architecture is highly promising for replacing encoder-based architectures in the field of 3D understanding. The code is released at https://github.com/Ivan-Tang-3D/ENEL

Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D domains. However, such 2D-to-3D approaches are still limited, due to the potential loss of spatial geometries and high computation cost. More importantly, their frameworks are mainly designed for 2D models, lacking a general any-to-3D paradigm. In this paper, we introduce Any2Point, a parameter-efficient method to empower any-modality large models (vision, language, audio) for 3D understanding. Given a frozen transformer from any source modality, we propose a 3D-to-any (1D or 2D) virtual projection strategy that correlates the input 3D points to the original 1D or 2D positions within the source modality. This mechanism enables us to assign each 3D token with a positional encoding paired with the pre-trained model, which avoids 3D geometry loss caused by the true projection and better motivates the transformer for 3D learning with 1D/2D positional priors. Then, within each transformer block, we insert an any-to-3D guided adapter module for parameter-efficient fine-tuning. The adapter incorporates prior spatial knowledge from the source modality to guide the local feature aggregation of 3D tokens, compelling the semantic adaption of any-modality transformers. We conduct extensive experiments to showcase the effectiveness and efficiency of our method. Code and models are released at https://github.com/Ivan-Tang-3D/Any2Point.

Abstract--This work reports a novel Bundle Adjustment (BA) formulation using a Reproducing Kernel Hilbert Space (RKHS) representation called RKHS-BA. The proposed formulation is correspondence-free, enables the BA to use RGB-D/LiDAR and semantic labels in the optimization directly, and provides a generalization for the photometric loss function commonly used in direct methods. RKHS-BA can incorporate appearance and semantic labels within a continuous spatial-semantic functional representation that does not require optimization via image pyramids. We demonstrate its applications in sliding-window odometry and global LiDAR mapping, which show highly robust performance in extremely challenging scenes and the best tradeoff of generalization and accuracy. I. INTRODUCTION Bundle Adjustment (BA) is widely used in visual perception algorithms such as Simultaneous Localization and Mapping (SLAM) and 3D Reconstruction. It jointly optimizes visual structures and all the camera parameters to construct a spatially-consistent 3D world model [73]. Then, in the optimization step, they minimize reprojected geometric residuals for features observed across multiple frames via multi-view geometry [36, 73]. However, full images need to be stored in the to sparse Hessian structures but relies on correct feature pose graph even in semi-dense approaches [95]. Many works have their illumination invariance presumption is seriously violated been devoted to improving their robustness, such as improving in outdoor situations where complex illumination, changeable frontend feature matching's quality with deep networks [33], weather, and dynamic objects exist. Specifically, we denote various types of visual information, feature association contaminated with outliers is still an open including pixel classes, object instances, intensities, problem [56].

Purpose: Common dense stereo Simultaneous Localization and Mapping (SLAM) approaches in Minimally Invasive Surgery (MIS) require high-end parallel computational resources for real-time implementation. Yet, it is not always feasible since the computational resources should be allocated to other tasks like segmentation, detection, and tracking. To solve the problem of limited parallel computational power, this research aims at a lightweight dense stereo SLAM system that works on a single-core CPU and achieves real-time performance (more than 30 Hz in typical scenarios). Methods: A new dense stereo mapping module is integrated with the ORB-SLAM2 system and named BDIS-SLAM. Our new dense stereo mapping module includes stereo matching and 3D dense depth mosaic methods. Stereo matching is achieved with the recently proposed CPU-level real-time matching algorithm Bayesian Dense Inverse Searching (BDIS). A BDIS-based shape recovery and a depth mosaic strategy are integrated as a new thread and coupled with the backbone ORB-SLAM2 system for real-time stereo shape recovery. Results: Experiments on in-vivo data sets show that BDIS-SLAM runs at over 30 Hz speed on modern single-core CPU in typical endoscopy/colonoscopy scenarios. BDIS-SLAM only consumes around an additional 12% time compared with the backbone ORB-SLAM2. Although our lightweight BDIS-SLAM simplifies the process by ignoring deformation and fusion procedures, it can provide a usable dense mapping for modern MIS on computationally constrained devices. Conclusion: The proposed BDIS-SLAM is a lightweight stereo dense SLAM system for MIS. It achieves 30 Hz on a modern single-core CPU in typical endoscopy/colonoscopy scenarios (image size around 640*480). BDIS-SLAM provides a low-cost solution for dense mapping in MIS and has the potential to be applied in surgical robots and AR systems.

The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost for downstream tasks, many Parameter-Efficient Fine-Tuning (PEFT) techniques are proposed for language and 2D image pre-trained models. However, the specialized PEFT method for 3D pre-trained models is still under-explored. To this end, we introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters. Specifically, for a pre-trained 3D model, we freeze most of its parameters, and only tune the newly added PEFT modules on downstream tasks, which consist of a Point-prior Prompt and a Geometry-aware Adapter. The Point-prior Prompt adopts a set of learnable prompt tokens, for which we propose to construct a memory bank with domain-specific knowledge, and utilize a parameter-free attention to enhance the prompt tokens. The Geometry-aware Adapter aims to aggregate point cloud features within spatial neighborhoods to capture fine-grained geometric information through local interactions. Extensive experiments indicate that our Point-PEFT can achieve better performance than the full fine-tuning on various downstream tasks, while using only 5% of the trainable parameters, demonstrating the efficiency and effectiveness of our approach. Code is released at https://github.com/Ivan-Tang-3D/PEFT-3D.

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality and fail to weigh the relative importance of different views. In this paper, we propose ViewRefer, a multi-view framework for 3D visual grounding exploring how to grasp the view knowledge from both text and 3D modalities. For the text branch, ViewRefer leverages the diverse linguistic knowledge of large-scale language models, e.g., GPT, to expand a single grounding text to multiple geometry-consistent descriptions. Meanwhile, in the 3D modality, a transformer fusion module with inter-view attention is introduced to boost the interaction of objects across views. On top of that, we further present a set of learnable multi-view prototypes, which memorize scene-agnostic knowledge for different views, and enhance the framework from two perspectives: a view-guided attention module for more robust text features, and a view-guided scoring strategy during the final prediction. With our designed paradigm, ViewRefer achieves superior performance on three benchmarks and surpasses the second-best by +2.8%, +1.5%, and +1.35% on Sr3D, Nr3D, and ScanRefer. Code is released at https://github.com/Ivan-Tang-3D/ViewRefer3D.