Recent advancements in 3D Large Multi-modal Models (3D-LMMs) have driven significant progress in 3D question answering. However, recent multi-frame Vision-Language Models (VLMs) demonstrate superior performance compared to 3D-LMMs on 3D question answering tasks, largely due to the greater scale and diversity of available 2D image data in contrast to the more limited 3D data. Multi-frame VLMs, although achieving superior performance, suffer from the difficulty of retaining all the detailed visual information in the 3D scene while limiting the number of visual tokens. Common methods such as token pooling, reduce visual token usage but often lead to information loss, impairing the model’s ability to preserve visual details essential for 3D question answering tasks. To address this, we propose voxel-based Dynamic Token Compression (DTC), which combines 3D spatial priors and visual semantics to achieve over 90% reduction in visual tokens usage for current multi-frame VLMs. Our method maintains performance comparable to state-of-the-art models on 3D question answering benchmarks including OpenEQA and ScanQA, demonstrating its effectiveness.

Unlike closed-vocabulary 3D instance segmentation that is often trained end-to-end, open-vocabulary 3D instance segmentation (OV-3DIS) often leverages vision-language models (VLMs) to generate 3D instance proposals and classify them. While various concepts have been proposed from existing research, we observe that these individual concepts are not mutually exclusive but complementary. In this paper, we propose a new state-of-the-art solution for OV-3DIS by carefully designing a recipe to combine the concepts together and refining them to address key challenges. Our solution follows the two-stage scheme: 3D proposal generation and instance classification. We employ robust 3D tracking-based proposal aggregation to generate 3D proposals and remove overlapped or partial proposals by iterative merging/removal. For the classification stage, we replace the standard CLIP model with Alpha-CLIP, which incorporates object masks as an alpha channel to reduce background noise and obtain object-centric representation. Additionally, we introduce the standardized maximum similarity (SMS) score to normalize text-to-proposal similarity, effectively filtering out false positives and boosting precision. Our framework achieves state-of-the-art performance on ScanNet200 and S3DIS across all AP and AR metrics, even surpassing an end-to-end closed-vocabulary method.

Reliable estimation of terrain traversability is critical for the successful deployment of autonomous systems in wild, outdoor environments. Given the lack of large-scale annotated datasets for off-road navigation, strictly-supervised learning approaches remain limited in their generalization ability. To this end, we introduce a novel, image-based self-supervised learning method for traversability prediction, leveraging a state-of-the-art vision foundation model for improved out-of-distribution performance. Our method employs contrastive representation learning using both human driving data and instance-based segmentation masks during training. We show that this simple, yet effective, technique drastically outperforms recent methods in predicting traversability for both on- and off-trail driving scenarios. We compare our method with recent baselines on both a common benchmark as well as our own datasets, covering a diverse range of outdoor environments and varied terrain types. We also demonstrate the compatibility of resulting costmap predictions with a model-predictive controller. Finally, we evaluate our approach on zero- and few-shot tasks, demonstrating unprecedented performance for generalization to new environments. Videos and additional material can be found here: https://sites.google.com/view/visual-traversability-learning.

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. TTA can be applied to pretrained networks without modifying their training procedures, enabling them to utilize a well-formed source distribution for adaptation. One possible approach is to align the representation space of test samples to the source distribution (i.e., feature alignment). However, performing feature alignment in TTA is especially challenging in that access to labeled source data is restricted during adaptation. That is, a model does not have a chance to learn test data in a class-discriminative manner, which was feasible in other adaptation tasks (e.g., unsupervised domain adaptation) via supervised losses on the source data. Based on this observation, we propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously 1) encourages a model to learn target representations in a class-discriminative manner and 2) effectively mitigates the distribution shifts at test time. Our method does not require any hyper-parameters or additional losses, which are required in previous approaches. We conduct extensive experiments on 6 different datasets and show our proposed method consistently outperforms existing baselines.

We introduce LiDAR-UDA, a novel two-stage self-training-based Unsupervised Domain Adaptation (UDA) method for LiDAR segmentation. Existing self-training methods use a model trained on labeled source data to generate pseudo labels for target data and refine the predictions via fine-tuning the network on the pseudo labels. These methods suffer from domain shifts caused by different LiDAR sensor configurations in the source and target domains. We propose two techniques to reduce sensor discrepancy and improve pseudo label quality: 1) Li-DAR beam subsampling, which simulates different LiDAR scanning patterns by randomly dropping beams; 2) cross-frame ensembling, which exploits temporal consistency of consecutive frames to generate more reliable pseudo labels. Our method is simple, generalizable, and does not incur any extra inference cost. We evaluate our method on several public LiDAR datasets and show that it outperforms the state-of-the-art methods by more than 3.9% mIoU on average for all scenarios. Code will be available at https://github.com/JHLee0513/lidar_uda.

Recent generative models based on neural radiance fields (NeRF) achieve the generation of diverse 3D-aware images. Despite the success, their applicability can be further expanded by incorporating with various types of user-specified conditions such as text and images. In this paper, we propose a novel approach called the conditional generative neural radiance fields (CG-NeRF), which generates multi-view images that reflect multimodal input conditions such as images or text. However, generating 3D-aware images from multimodal conditions bears several challenges. First, each condition type has different amount of information - e.g., the amount of information in text and color images are significantly different. Furthermore, the pose-consistency is often violated when diversifying the generated images from input conditions. Addressing such challenges, we propose 1) a unified architecture that effectively handles multiple types of conditions, and 2) the pose-consistent diversity loss for generating various images while maintaining the view consistency. Experimental results show that the proposed method maintains consistent image quality on various multimodal condition types and achieves superior fidelity and diversity compared to the existing NeRF-based generative models.

Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To address this issue, this paper proposes a novel instance selective whitening loss to improve the robustness of the segmentation networks for unseen domains. Our approach disentangles the domain-specific style and domain-invariant content encoded in higher-order statistics (i.e., feature covariance) of the feature representations and selectively removes only the style information causing domain shift. As shown in Fig. 1, our method provides reasonable predictions for (a) low-illuminated, (b) rainy, and (c) unseen structures. These types of images are not included in the training dataset, where the baseline shows a significant performance drop, contrary to ours. Being simple yet effective, our approach improves the robustness of various backbone networks without additional computational cost. We conduct extensive experiments in urban-scene segmentation and show the superiority of our approach to existing work. Our code is available at this link1.

Identifying unexpected objects on roads in semantic segmentation (e.g., identifying dogs on roads) is crucial in safetycritical applications. Existing approaches use images of unexpected objects from external datasets or require additional training (e.g., retraining segmentation networks or training an extra network), which necessitate a non-trivial amount of labor intensity or lengthy inference time. One possible alternative is to use prediction scores of a pretrained network such as the max logits (i.e., maximum values among classes before the final softmax layer) for detecting such objects. However, the distribution of max logits of each predicted class is significantly different from each other, which degrades the performance of identifying unexpected objects in urban-scene segmentation. To address this issue, we propose a simple yet effective approach that standardizes the max logits in order to align the different distributions and reflect the relative meanings of max logits within each predicted class. Moreover, we consider the local regions from two different perspectives based on the intuition that neighboring pixels share similar semantic information. In contrast to previous approaches, our method does not utilize any external datasets or require additional training, which makes our method widely applicable to existing pretrained segmentation models. Such a straightforward approach achieves a new state-of-the-art performance on the publicly available Fishyscapes Lost & Found leader-board with a large margin. Our code is publicly available at this link1.

Abstract The majority of visualizations on the web are still stored as raster images, making them inaccessible to visually impaired users. We propose a deep‐neural‐network‐based approach that automatically recognizes key elements in a visualization, including a visualization type, graphical elements, labels, legends, and most importantly, the original data conveyed in the visualization. We leverage such extracted information to provide visually impaired people with the reading of the extracted information. Based on interviews with visually impaired users, we built a Google Chrome extension designed to work with screen reader software to automatically decode charts on a webpage using our pipeline. We compared the performance of the back‐end algorithm with existing methods and evaluated the utility using qualitative feedback from visually impaired users.