Chun-Peng Chang

Chun-Peng Chang, Shaoxiang Wang, Alain Pagani et al.

Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain. We investigate the failure of 3D point cloud encoders to achieve similar generalization and find that existing models are highly sensitive to sampling resolution and scale changes, leading to significant performance degradation. This sensitivity is a major bottleneck for real-world deployment in robotics, as it suggests models overfit to specific quantization densities and object scales rather than learning invariant semantic features. To mitigate this dependency, we propose Invaria, a point cloud encoder that achieves scale and density invariance through next-resolution prediction and receptive field calibration. While our objective is not the explicit generation of high-resolution point clouds, we find that this training objective encourages the model to learn robust, structural invariants. The resulting encoder achieves significant performance gains during resolution shifts while maintaining high efficiency through a compact model size and reduced token requirements. Specifically, on ScanNet, Invaria achieves a 56.0\% higher mIoU at 3$\times$ lower resolution and a 20\% improvement when the objects scale is reduced by a factor of 3. These gains are achieved with a 45\% smaller model size and an average reduction of 40\% in input tokens.

Chun-Peng Chang, Chen-Yu Wang, Holger Caesar et al.

A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Vision-Language Models (VLMs), when applied as driving assistants, can response consistantly and understand how present observations shape future outcomes, or whether their outputs merely reflect patterns memorized during training without temporally grounded reasoning. While recent efforts have integrated VLMs into autonomous driving, prior studies typically emphasize scene understanding and instruction generation, implicitly assuming that strong visual interpretation naturally enables consistant future reasoning and thus ensures reliable decision-making, a claim we critically examine. We focus on two major challenges limiting VLM reliability in this setting: response inconsistency, where minor input perturbations yield different answers or, in some cases, responses degenerate toward near-random guessing, and limited temporal reasoning, in which models fail to reason and align sequential events from current observations, often resulting in incorrect or even contradictory responses. Moreover, we find that models with strong visual understanding do not necessarily perform best on tasks requiring temporal reasoning, indicating a tendency to over-rely on pretrained patterns rather than modeling temporal dynamics. To address these issues, we adopt existing evaluation methods and introduce FutureVQA, a human-annotated benchmark dataset specifically designed to assess future scene reasoning. In addition, we propose a simple yet effective self-supervised tuning approach with chain-of-thought reasoning that improves both consistency and temporal reasoning without requiring temporal labels.

Chun-Peng Chang, Shaoxiang Wang, Alain Pagani et al.

3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.

Shaoxiang Wang, Yaxu Xie, Chun-Peng Chang et al.

Neural implicit fields have recently emerged as a powerful representation method for multi-view surface reconstruction due to their simplicity and state-of-the-art performance. However, reconstructing thin structures of indoor scenes while ensuring real-time performance remains a challenge for dense visual SLAM systems. Previous methods do not consider varying quality of input RGB-D data and employ fixed-frequency mapping process to reconstruct the scene, which could result in the loss of valuable information in some frames. In this paper, we propose Uni-SLAM, a decoupled 3D spatial representation based on hash grids for indoor reconstruction. We introduce a novel defined predictive uncertainty to reweight the loss function, along with strategic local-to-global bundle adjustment. Experiments on synthetic and real-world datasets demonstrate that our system achieves state-of-the-art tracking and mapping accuracy while maintaining real-time performance. It significantly improves over current methods with a 25% reduction in depth L1 error and a 66.86% completion rate within 1 cm on the Replica dataset, reflecting a more accurate reconstruction of thin structures. Project page: https://shaoxiang777.github.io/project/uni-slam/

Chun-Peng Chang, Chen-Yu Wang, Julian Schmidt et al.

Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as autonomous driving, particularly in the context of driving simulation and so-called "world models". In this work, we investigate the effects of existing fine-tuning video generation approaches on structured driving datasets and uncover a potential trade-off: although visual fidelity improves, spatial accuracy in modeling dynamic elements may degrade. We attribute this degradation to a shift in the alignment between visual quality and dynamic understanding objectives. In datasets with diverse scene structures within temporal space, where objects or perspective shift in varied ways, these objectives tend to highly correlated. However, the very regular and repetitive nature of driving scenes allows visual quality to improve by modeling dominant scene motion patterns, without necessarily preserving fine-grained dynamic behavior. As a result, fine-tuning encourages the model to prioritize surface-level realism over dynamic accuracy. To further examine this phenomenon, we show that simple continual learning strategies, such as replay from diverse domains, can offer a balanced alternative by preserving spatial accuracy while maintaining strong visual quality.

Chun-Peng Chang, Alain Pagani, Didier Stricker

Multimodal Large Language Models (MLLMs) have made significant progress in tasks such as image captioning and question answering. However, while these models can generate realistic captions, they often struggle with providing precise instructions, particularly when it comes to localizing and disambiguating objects in complex 3D environments. This capability is critical as MLLMs become more integrated with collaborative robotic systems. In scenarios where a target object is surrounded by similar objects (distractors), robots must deliver clear, spatially-aware instructions to guide humans effectively. We refer to this challenge as contextual object localization and disambiguation, which imposes stricter constraints than conventional 3D dense captioning, especially regarding ensuring target exclusivity. In response, we propose simple yet effective techniques to enhance the model's ability to localize and disambiguate target objects. Our approach not only achieves state-of-the-art performance on conventional metrics that evaluate sentence similarity, but also demonstrates improved 3D spatial understanding through 3D visual grounding model.