We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained backbone, we pretrain the backbone using image-depth pairs from ImageNet-1K, and hence the DFormer is endowed with the capacity to encode RGB-D representations; 2) DFormer comprises a sequence of RGB-D blocks, which are tailored for encoding both RGB and depth information through a novel building block design. DFormer avoids the mismatched encoding of the 3D geometry relationships in depth maps by RGB pretrained backbones, which widely lies in existing methods but has not been resolved. We finetune the pretrained DFormer on two popular RGB-D tasks, i.e., RGB-D semantic segmentation and RGB-D salient object detection, with a lightweight decoder head. Experimental results show that our DFormer achieves new state-of-the-art performance on these two tasks with less than half of the computational cost of the current best methods on two RGB-D semantic segmentation datasets and five RGB-D salient object detection datasets. Our code is available at: //github.com/VCIP-RGBD/DFormer.
相關內容
Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to synthesize quasi-static videos, ignoring the necessary visual change-over-time implied in the text prompt. At the same time, scaling these models to enable longer, more dynamic video synthesis often remains computationally intractable. To address this challenge, we introduce the concept of Generative Temporal Nursing (GTN), where we aim to alter the generative process on the fly during inference to improve control over the temporal dynamics and enable generation of longer videos. We propose a method for GTN, dubbed VSTAR, which consists of two key ingredients: 1) Video Synopsis Prompting (VSP) - automatic generation of a video synopsis based on the original single prompt leveraging LLMs, which gives accurate textual guidance to different visual states of longer videos, and 2) Temporal Attention Regularization (TAR) - a regularization technique to refine the temporal attention units of the pre-trained T2V diffusion models, which enables control over the video dynamics. We experimentally showcase the superiority of the proposed approach in generating longer, visually appealing videos over existing open-sourced T2V models. We additionally analyze the temporal attention maps realized with and without VSTAR, demonstrating the importance of applying our method to mitigate neglect of the desired visual change over time.
We introduce EscherNet, a multi-view conditioned diffusion model for view synthesis. EscherNet learns implicit and generative 3D representations coupled with a specialised camera positional encoding, allowing precise and continuous relative control of the camera transformation between an arbitrary number of reference and target views. EscherNet offers exceptional generality, flexibility, and scalability in view synthesis -- it can generate more than 100 consistent target views simultaneously on a single consumer-grade GPU, despite being trained with a fixed number of 3 reference views to 3 target views. As a result, EscherNet not only addresses zero-shot novel view synthesis, but also naturally unifies single- and multi-image 3D reconstruction, combining these diverse tasks into a single, cohesive framework. Our extensive experiments demonstrate that EscherNet achieves state-of-the-art performance in multiple benchmarks, even when compared to methods specifically tailored for each individual problem. This remarkable versatility opens up new directions for designing scalable neural architectures for 3D vision. Project page: //kxhit.github.io/EscherNet.
This paper presents a novel split learning (SL) framework, referred to as SplitMAC, which reduces the latency of SL by leveraging simultaneous uplink transmission over multiple access channels. The key strategy is to divide devices into multiple groups and allow the devices within the same group to simultaneously transmit their smashed data and device-side models over the multiple access channels. The optimization problem of device grouping to minimize SL latency is formulated, and the benefit of device grouping in reducing the uplink latency of SL is theoretically derived. By examining a two-device grouping case, two asymptotically-optimal algorithms are devised for device grouping in low and high signal-to-noise ratio (SNR) scenarios, respectively, while providing proofs of their optimality. By merging these algorithms, a near-optimal device grouping algorithm is proposed to cover a wide range of SNR. Our SL framework is also extended to consider practical fading channels and to support a general group size. Simulation results demonstrate that our SL framework with the proposed device grouping algorithm is superior to existing SL frameworks in reducing SL latency.
This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generates augmented point prompts to provide more information about the user's intention to SAM. Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts. By incorporating these extra points, SAM can generate augmented segmentation masks based on both the augmented point prompts and the initial prompt, resulting in improved segmentation performance. We conducted evaluations using four different point augmentation strategies: random sampling, sampling based on maximum difference entropy, maximum distance, and saliency. Experiment results on the COCO, Fundus, COVID QUEx, and ISIC2018 datasets show that SAMAug can boost SAM's segmentation results, especially using the maximum distance and saliency. SAMAug demonstrates the potential of visual prompt augmentation for computer vision. Codes of SAMAug are available at github.com/yhydhx/SAMAug
This paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation. With the assistance of the state-of-the-art real-time open-world object detection model Yolo-World and specialized prompts, the proposed framework can identify anomalies within camera-captured frames that include any possible obstacles, then generate concise, audio-delivered descriptions emphasizing abnormalities, assist in safe visual navigation in complex circumstances. Moreover, our proposed framework leverages the advantages of LLMs and the open-vocabulary object detection model to achieve the dynamic scenario switch, which allows users to transition smoothly from scene to scene, which addresses the limitation of traditional visual navigation. Furthermore, this paper explored the performance contribution of different prompt components, provided the vision for future improvement in visual accessibility, and paved the way for LLMs in video anomaly detection and vision-language understanding.
In this work, we introduce the Virtual In-Hand Eye Transformer (VIHE), a novel method designed to enhance 3D manipulation capabilities through action-aware view rendering. VIHE autoregressively refines actions in multiple stages by conditioning on rendered views posed from action predictions in the earlier stages. These virtual in-hand views provide a strong inductive bias for effectively recognizing the correct pose for the hand, especially for challenging high-precision tasks such as peg insertion. On 18 manipulation tasks in RLBench simulated environments, VIHE achieves a new state-of-the-art, with a 12% absolute improvement, increasing from 65% to 77% over the existing state-of-the-art model using 100 demonstrations per task. In real-world scenarios, VIHE can learn manipulation tasks with just a handful of demonstrations, highlighting its practical utility. Videos and code implementation can be found at our project site: //vihe-3d.github.io.
This paper presents a novel system designed for 3D mapping and visual relocalization using 3D Gaussian Splatting. Our proposed method uses LiDAR and camera data to create accurate and visually plausible representations of the environment. By leveraging LiDAR data to initiate the training of the 3D Gaussian Splatting map, our system constructs maps that are both detailed and geometrically accurate. To mitigate excessive GPU memory usage and facilitate rapid spatial queries, we employ a combination of a 2D voxel map and a KD-tree. This preparation makes our method well-suited for visual localization tasks, enabling efficient identification of correspondences between the query image and the rendered image from the Gaussian Splatting map via normalized cross-correlation (NCC). Additionally, we refine the camera pose of the query image using feature-based matching and the Perspective-n-Point (PnP) technique. The effectiveness, adaptability, and precision of our system are demonstrated through extensive evaluation on the KITTI360 dataset.
We present GigaPose, a fast, robust, and accurate method for CAD-based novel object pose estimation in RGB images. GigaPose first leverages discriminative "templates", rendered images of the CAD models, to recover the out-of-plane rotation and then uses patch correspondences to estimate the four remaining parameters. Our approach samples templates in only a two-degrees-of-freedom space instead of the usual three and matches the input image to the templates using fast nearest-neighbor search in feature space, results in a speedup factor of 35x compared to the state of the art. Moreover, GigaPose is significantly more robust to segmentation errors. Our extensive evaluation on the seven core datasets of the BOP challenge demonstrates that it achieves state-of-the-art accuracy and can be seamlessly integrated with existing refinement methods. Additionally, we show the potential of GigaPose with 3D models predicted by recent work on 3D reconstruction from a single image, relaxing the need for CAD models and making 6D pose object estimation much more convenient. Our source code and trained models are publicly available at //github.com/nv-nguyen/gigaPose
We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability. It also learns to perform screenshot tasks through finetuning. Evaluation on 12 benchmarks shows notable improvements: 5.2% in Scene Text-Centric tasks (including STVQA, TextVQA, and OCRVQA), 6.9% in Document-Oriented tasks (such as DocVQA, InfoVQA, ChartVQA, DeepForm, Kleister Charity, and WikiTableQuestions), and 2.8% in Key Information Extraction tasks (comprising FUNSD, SROIE, and POIE). It outperforms in scene text spotting with a 10.9\% increase and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding. Code will be released at //github.com/Yuliang-Liu/Monkey.
We present CoDEx, a set of knowledge graph completion datasets extracted from Wikidata and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. In terms of scope, CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible but verified to be false. To characterize CoDEx, we contribute thorough empirical analyses and benchmarking experiments. First, we analyze each CoDEx dataset in terms of logical relation patterns. Next, we report baseline link prediction and triple classification results on CoDEx for five extensively tuned embedding models. Finally, we differentiate CoDEx from the popular FB15K-237 knowledge graph completion dataset by showing that CoDEx covers more diverse and interpretable content, and is a more difficult link prediction benchmark. Data, code, and pretrained models are available at //bit.ly/2EPbrJs.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191