Yen-Yu Lin

Cheng-Ju Ho, Chen-Hsuan Tai, Yi-Hsuan Tsai et al.

Semi-supervised object detection is important for 3D scene understanding because obtaining large-scale 3D bounding box annotations on point clouds is time-consuming and labor-intensive. Existing semi-supervised methods usually employ teacher-student knowledge distillation together with an augmentation strategy to leverage unlabeled point clouds. However, these methods adopt global augmentation with scene-level transformations and hence are sub-optimal for instance-level object detection. In this work, we propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection. In this way, the resultant augmentor is derived to emphasize object instances rather than irrelevant backgrounds, making the augmented data more useful for object detector training. Extensive experiments on the ScanNet and SUN RGB-D datasets show that the proposed OPA performs favorably against the state-of-the-art methods under various experimental settings. The source code will be available at https://github.com/nomiaro/OPA.

Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin et al.

Images taken in dynamic scenes may contain unwanted motion blur, which significantly degrades visual quality. Such blur causes short- and long-range region-specific smoothing artifacts that are often directional and non-uniform, which is difficult to be removed. Inspired by the current success of transformers on computer vision and image processing tasks, we develop, Stripformer, a transformer-based architecture that constructs intra- and inter-strip tokens to reweight image features in the horizontal and vertical directions to catch blurred patterns with different orientations. It stacks interlaced intra-strip and inter-strip attention layers to reveal blur magnitudes. In addition to detecting region-specific blurred patterns of various orientations and magnitudes, Stripformer is also a token-efficient and parameter-efficient transformer model, demanding much less memory usage and computation cost than the vanilla transformer but works better without relying on tremendous training data. Experimental results show that Stripformer performs favorably against state-of-the-art models in dynamic scene deblurring.

Su-Kai Chen, Hung-Lin Yen, Yu-Lun Liu et al. · nvidia

Deep learning is commonly used to reconstruct HDR images from LDR images. LDR stack-based methods are used for single-image HDR reconstruction, generating an HDR image from a deep learning-generated LDR stack. However, current methods generate the stack with predetermined exposure values (EVs), which may limit the quality of HDR reconstruction. To address this, we propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training. Our approach generates a continuous stack with more images containing diverse EVs, significantly improving HDR reconstruction. We use a cycle training strategy to supervise the model in generating continuous EV LDR images without corresponding ground truths. Our CEVR model outperforms existing methods, as demonstrated by experimental results.

Jin-Ting He, Fu-Jen Tsai, Jia-Hao Wu et al.

Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due to the domain gap between training and testing videos, especially for those captured in real-world scenarios. To address this issue, we propose a domain adaptation scheme based on a blurring model to achieve test-time fine-tuning for deblurring models in unseen domains. Since blurred and sharp pairs are unavailable for fine-tuning during inference, our scheme can generate domain-adaptive training pairs to calibrate a deblurring model for the target domain. First, a Relative Sharpness Detection Module is proposed to identify relatively sharp regions from the blurry input images and regard them as pseudo-sharp images. Next, we utilize a blurring model to produce blurred images based on the pseudo-sharp images extracted during testing. To synthesize blurred images in compliance with the target data distribution, we propose a Domain-adaptive Blur Condition Generation Module to create domain-specific blur conditions for the blurring model. Finally, the generated pseudo-sharp and blurred pairs are used to fine-tune a deblurring model for better performance. Extensive experimental results demonstrate that our approach can significantly improve state-of-the-art video deblurring methods, providing performance gains of up to 7.54dB on various real-world video deblurring datasets. The source code is available at https://github.com/Jin-Ting-He/DADeblur.

Po-Sheng Liu, Fu-Jen Tsai, Yan-Tsung Peng et al.

Most previous deblurring methods were built with a generic model trained on blurred images and their sharp counterparts. However, these approaches might have sub-optimal deblurring results due to the domain gap between the training and test sets. This paper proposes a reblur-deblur meta-transferring scheme to realize test-time adaptation without using ground truth for dynamic scene deblurring. Since the ground truth is usually unavailable at inference time in a real-world scenario, we leverage the blurred input video to find and use relatively sharp patches as the pseudo ground truth. Furthermore, we propose a reblurring model to extract the homogenous blur from the blurred input and transfer it to the pseudo-sharps to obtain the corresponding pseudo-blurred patches for meta-learning and test-time adaptation with only a few gradient updates. Extensive experimental results show that our reblur-deblur meta-learning scheme can improve state-of-the-art deblurring models on the DVD, REDS, and RealBlur benchmark datasets.

Jin-Ting He, Fu-Jen Tsai, Yan-Tsung Peng et al.

Diffusion models show promise for dynamic scene deblurring; however, existing studies often fail to leverage the intrinsic nature of the blurring process within diffusion models, limiting their full potential. To address it, we present a Blur Diffusion Model (BlurDM), which seamlessly integrates the blur formation process into diffusion for image deblurring. Observing that motion blur stems from continuous exposure, BlurDM implicitly models the blur formation process through a dual-diffusion forward scheme, diffusing both noise and blur onto a sharp image. During the reverse generation process, we derive a dual denoising and deblurring formulation, enabling BlurDM to recover the sharp image by simultaneously denoising and deblurring, given pure Gaussian noise conditioned on the blurred image as input. Additionally, to efficiently integrate BlurDM into deblurring networks, we perform BlurDM in the latent space, forming a flexible prior generation network for deblurring. Extensive experiments demonstrate that BlurDM significantly and consistently enhances existing deblurring methods on four benchmark datasets. The source code is available at https://github.com/Jin-Ting-He/BlurDM.

Yo-Tin Lin, Su-Kai Chen, Hou-Ning Hu et al.

Single LDR to HDR reconstruction remains challenging for over-exposed regions where traditional methods often fail due to complete information loss. We present a training-free approach that enhances existing indirect and direct HDR reconstruction methods through diffusion-based inpainting. Our method combines text-guided diffusion models with SDEdit refinement to generate plausible content in over-exposed areas while maintaining consistency across multi-exposure LDR images. Unlike previous approaches requiring extensive training, our method seamlessly integrates with existing HDR reconstruction techniques through an iterative compensation mechanism that ensures luminance coherence across multiple exposures. We demonstrate significant improvements in both perceptual quality and quantitative metrics on standard HDR datasets and in-the-wild captures. Results show that our method effectively recovers natural details in challenging scenarios while preserving the advantages of existing HDR reconstruction pipelines. Project page: https://github.com/EusdenLin/HDR-Reconstruction-Boosting

Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo et al.

Learning a discriminative model to distinguish a target from its surrounding distractors is essential to generic visual object tracking. Dynamic target representation adaptation against distractors is challenging due to the limited discriminative capabilities of prevailing trackers. We present a new visual Prompting mechanism for generic Visual Object Tracking (PiVOT) to address this issue. PiVOT proposes a prompt generation network with the pre-trained foundation model CLIP to automatically generate and refine visual prompts, enabling the transfer of foundation model knowledge for tracking. While CLIP offers broad category-level knowledge, the tracker, trained on instance-specific data, excels at recognizing unique object instances. Thus, PiVOT first compiles a visual prompt highlighting potential target locations. To transfer the knowledge of CLIP to the tracker, PiVOT leverages CLIP to refine the visual prompt based on the similarities between candidate objects and the reference templates across potential targets. Once the visual prompt is refined, it can better highlight potential target locations, thereby reducing irrelevant prompt information. With the proposed prompting mechanism, the tracker can generate improved instance-aware feature maps through the guidance of the visual prompt, thus effectively reducing distractors. The proposed method does not involve CLIP during training, thereby keeping the same training complexity and preserving the generalization capability of the pretrained foundation model. Extensive experiments across multiple benchmarks indicate that PiVOT, using the proposed prompting method can suppress distracting objects and enhance the tracker.

Cheng-Kun Yang, Min-Hung Chen, Yung-Yu Chuang et al.

We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and 3D data for weakly supervised point cloud segmentation. Research studies have shown that 2D and 3D features are complementary for point cloud segmentation. However, existing methods require extra 2D annotations to achieve 2D-3D information fusion. Considering the high annotation cost of point clouds, effective 2D and 3D feature fusion based on weakly supervised learning is in great demand. To this end, we propose a transformer model with two encoders and one decoder for weakly supervised point cloud segmentation using only scene-level class tags. Specifically, the two encoders compute the self-attended features for 3D point clouds and 2D multi-view images, respectively. The decoder implements interlaced 2D-3D cross-attention and carries out implicit 2D and 3D feature fusion. We alternately switch the roles of queries and key-value pairs in the decoder layers. It turns out that the 2D and 3D features are iteratively enriched by each other. Experiments show that it performs favorably against existing weakly supervised point cloud segmentation methods by a large margin on the S3DIS and ScanNet benchmarks. The project page will be available at https://jimmy15923.github.io/mit_web/.

Ardian Umam, Cheng-Kun Yang, Min-Hung Chen et al.

This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation. PartDistill addresses three major challenges in this task: the lack of 3D segmentation in invisible or undetected regions in the 2D projections, inconsistent 2D predictions by VLMs, and the lack of knowledge accumulation across different 3D shapes. PartDistill consists of a teacher network that uses a VLM to make 2D predictions and a student network that learns from the 2D predictions while extracting geometrical features from multiple 3D shapes to carry out 3D part segmentation. A bi-directional distillation, including forward and backward distillations, is carried out within the framework, where the former forward distills the 2D predictions to the student network, and the latter improves the quality of the 2D predictions, which subsequently enhances the final 3D segmentation. Moreover, PartDistill can exploit generative models that facilitate effortless 3D shape creation for generating knowledge sources to be distilled. Through extensive experiments, PartDistill boosts the existing methods with substantial margins on widely used ShapeNetPart and PartNetE datasets, by more than 15% and 12% higher mIoU scores, respectively. The code for this work is available at https://github.com/ardianumam/PartDistill.

Jia-Hao Wu, Fu-Jen Tsai, Yan-Tsung Peng et al.

Image deblurring aims to remove undesired blurs from an image captured in a dynamic scene. Much research has been dedicated to improving deblurring performance through model architectural designs. However, there is little work on data augmentation for image deblurring. Since continuous motion causes blurred artifacts during image exposure, we aspire to develop a groundbreaking blur augmentation method to generate diverse blurred images by simulating motion trajectories in a continuous space. This paper proposes Implicit Diffusion-based reBLurring AUgmentation (ID-Blau), utilizing a sharp image paired with a controllable blur condition map to produce a corresponding blurred image. We parameterize the blur patterns of a blurred image with their orientations and magnitudes as a pixel-wise blur condition map to simulate motion trajectories and implicitly represent them in a continuous space. By sampling diverse blur conditions, ID-Blau can generate various blurred images unseen in the training set. Experimental results demonstrate that ID-Blau can produce realistic blurred images for training and thus significantly improve performance for state-of-the-art deblurring models. The source code is available at https://github.com/plusgood-steven/ID-Blau.

Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo et al.

Human perception for effective object tracking in a 2D video stream arises from the implicit use of prior 3D knowledge combined with semantic reasoning. In contrast, most generic object tracking (GOT) methods primarily rely on 2D features of the target and its surroundings while neglecting 3D geometric cues, which makes them susceptible to partial occlusion, distractors, and variations in geometry and appearance. To address this limitation, we introduce GOT-Edit, an online cross-modality model editing approach that integrates geometry-aware cues into a generic object tracker from a 2D video stream. Our approach leverages features from a pre-trained Visual Geometry Grounded Transformer to enable geometric cue inference from only a few 2D images. To tackle the challenge of seamlessly combining geometry and semantics, GOT-Edit performs online model editing with null-space constrained updates that incorporate geometric information while preserving semantic discrimination, yielding consistently better performance across diverse scenarios. Extensive experiments on multiple GOT benchmarks demonstrate that GOT-Edit achieves superior robustness and accuracy, particularly under occlusion and clutter, establishing a new paradigm for combining 2D semantics with 3D geometric reasoning for generic object tracking.

Jingcheng Ke, Dele Wang, Jun-Cheng Chen et al.

One common belief is that with complex models and pre-training on large-scale datasets, transformer-based methods for referring expression comprehension (REC) perform much better than existing graph-based methods. We observe that since most graph-based methods adopt an off-the-shelf detector to locate candidate objects (i.e., regions detected by the object detector), they face two challenges that result in subpar performance: (1) the presence of significant noise caused by numerous irrelevant objects during reasoning, and (2) inaccurate localization outcomes attributed to the provided detector. To address these issues, we introduce a plug-and-adapt module guided by sub-expressions, called dynamic gate constraint (DGC), which can adaptively disable irrelevant proposals and their connections in graphs during reasoning. We further introduce an expression-guided regression strategy (EGR) to refine location prediction. Extensive experimental results on the RefCOCO, RefCOCO+, RefCOCOg, Flickr30K, RefClef, and Ref-reasoning datasets demonstrate the effectiveness of the DGC module and the EGR strategy in consistently boosting the performances of various graph-based REC methods. Without any pretaining, the proposed graph-based method achieves better performance than the state-of-the-art (SOTA) transformer-based methods.

Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo et al.

The human visual system tracks objects by integrating current observations with previously observed information, adapting to target and scene changes, and reasoning about occlusion at fine granularity. In contrast, recent generic object trackers are often optimized for training targets, which limits robustness and generalization in unseen scenarios, and their occlusion reasoning remains coarse, lacking detailed modeling of occlusion patterns. To address these limitations in generalization and occlusion perception, we propose GOT-JEPA, a model-predictive pretraining framework that extends JEPA from predicting image features to predicting tracking models. Given identical historical information, a teacher predictor generates pseudo-tracking models from a clean current frame, and a student predictor learns to predict the same pseudo-tracking models from a corrupted version of the current frame. This design provides stable pseudo supervision and explicitly trains the predictor to produce reliable tracking models under occlusions, distractors, and other adverse observations, improving generalization to dynamic environments. Building on GOT-JEPA, we further propose OccuSolver to enhance occlusion perception for object tracking. OccuSolver adapts a point-centric point tracker for object-aware visibility estimation and detailed occlusion-pattern capture. Conditioned on object priors iteratively generated by the tracker, OccuSolver incrementally refines visibility states, strengthens occlusion handling, and produces higher-quality reference labels that progressively improve subsequent model predictions. Extensive evaluations on seven benchmarks show that our method effectively enhances tracker generalization and robustness.

Yi-Jen Tsai, Yen-Yu Lin, Chien-Yao Wang

Few-Shot Semantic Segmentation (FSS) focuses on segmenting novel object categories from only a handful of annotated examples. Most existing approaches rely on extensive episodic training to learn transferable representations, which is both computationally demanding and sensitive to distribution shifts. In this work, we revisit FSS from the perspective of modern vision foundation models and explore the potential of Segment Anything Model 3 (SAM3) as a training-free solution. By repurposing its Promptable Concept Segmentation (PCS) capability, we adopt a simple spatial concatenation strategy that places support and query images into a shared canvas, allowing a fully frozen SAM3 to perform segmentation without any fine-tuning or architectural changes. Experiments on PASCAL-$5^i$ and COCO-$20^i$ show that this minimal design already achieves state-of-the-art performance, outperforming many heavily engineered methods. Beyond empirical gains, we uncover that negative prompts can be counterproductive in few-shot settings, where they often weaken target representations and lead to prediction collapse despite their intended role in suppressing distractors. These findings suggest that strong cross-image reasoning can emerge from simple spatial formulations, while also highlighting limitations in how current foundation models handle conflicting prompt signals. Code at: https://github.com/WongKinYiu/FSS-SAM3

Wei-Hsiang Yu, Yen-Yu Lin, Ming-Hsuan Yang et al.

Recent advances in vision-language models (VLMs) have made significant progress in downstream tasks that require quantitative concepts such as facial age estimation and image quality assessment, enabling VLMs to explore applications like image ranking and retrieval. However, existing studies typically focus on the reasoning based on a single image and heavily depend on text prompting, limiting their ability to learn comprehensive understanding from multiple images. To address this, we propose an effective yet efficient approach that reframes the CLIP model into a learning-to-rank task and introduces a lightweight adapter to augment CLIP for text-guided image ranking. Specifically, our approach incorporates learnable prompts to adapt to new instructions for ranking purposes and an auxiliary branch with ranking-aware attention, leveraging text-conditioned visual differences for additional supervision in image ranking. Our ranking-aware adapter consistently outperforms fine-tuned CLIPs on various tasks and achieves competitive results compared to state-of-the-art models designed for specific tasks like facial age estimation and image quality assessment. Overall, our approach primarily focuses on ranking images with a single instruction, which provides a natural and generalized way of learning from visual differences across images, bypassing the need for extensive text prompts tailored to individual tasks. Code is available: github.com/uynaes/RankingAwareCLIP.

Yang-Che Sun, Cheng Sun, Chin-Yang Lin et al.

Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional 3D instance segmentation methods address viewpoint consistency but require camera poses, depth maps, and expensive preprocessing. We introduce 3AM, a training-time enhancement that integrates 3D-aware features from MUSt3R into SAM2. Our lightweight Feature Merger fuses multi-level MUSt3R features that encode implicit geometric correspondence. Combined with SAM2's appearance features, the model achieves geometry-consistent recognition grounded in both spatial position and visual similarity. We propose a field-of-view aware sampling strategy ensuring frames observe spatially consistent object regions for reliable 3D correspondence learning. Critically, our method requires only RGB input at inference, with no camera poses or preprocessing. On challenging datasets with wide-baseline motion (ScanNet++, Replica), 3AM substantially outperforms SAM2 and extensions, achieving 90.6% IoU and 71.7% Positive IoU on ScanNet++'s Selected Subset, improving over state-of-the-art VOS methods by +15.9 and +30.4 points. Project page: https://jayisaking.github.io/3AM-Page/

Liangjian Chen, Shih-Yao Lin, Yusheng Xie et al.

Estimating 3D hand poses from a single RGB image is challenging because depth ambiguity leads the problem ill-posed. Training hand pose estimators with 3D hand mesh annotations and multi-view images often results in significant performance gains. However, existing multi-view datasets are relatively small with hand joints annotated by off-the-shelf trackers or automated through model predictions, both of which may be inaccurate and can introduce biases. Collecting a large-scale multi-view 3D hand pose images with accurate mesh and joint annotations is valuable but strenuous. In this paper, we design a spin match algorithm that enables a rigid mesh model matching with any target mesh ground truth. Based on the match algorithm, we propose an efficient pipeline to generate a large-scale multi-view hand mesh (MVHM) dataset with accurate 3D hand mesh and joint labels. We further present a multi-view hand pose estimation approach to verify that training a hand pose estimator with our generated dataset greatly enhances the performance. Experimental results show that our approach achieves the performance of 0.990 in $\text{AUC}_{\text{20-50}}$ on the MHP dataset compared to the previous state-of-the-art of 0.939 on this dataset. Our datasset is public available. \footnote{\url{https://github.com/Kuzphi/MVHM}} Our datasset is available at~\href{https://github.com/Kuzphi/MVHM}{\color{blue}{https://github.com/Kuzphi/MVHM}}.

Zhenyu Wu, Duc Hoang, Shih-Yao Lin et al.

Estimating the 3D hand pose from a monocular RGB image is important but challenging. A solution is training on large-scale RGB hand images with accurate 3D hand keypoint annotations. However, it is too expensive in practice. Instead, we have developed a learning-based approach to synthesize realistic, diverse, and 3D pose-preserving hand images under the guidance of 3D pose information. We propose a 3D-aware multi-modal guided hand generative network (MM-Hand), together with a novel geometry-based curriculum learning strategy. Our extensive experimental results demonstrate that the 3D-annotated images generated by MM-Hand qualitatively and quantitatively outperform existing options. Moreover, the augmented data can consistently improve the quantitative performance of the state-of-the-art 3D hand pose estimators on two benchmark datasets. The code will be available at https://github.com/ScottHoang/mm-hand.

Cheng-Ju Ho, Chen-Hsuan Tai, Yen-Yu Lin et al.

Semi-supervised object detection is crucial for 3D scene understanding, efficiently addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing methods typically employ a teacher-student framework with pseudo-labeling to leverage unlabeled point clouds. However, producing reliable pseudo-labels in a diverse 3D space still remains challenging. In this work, we propose Diffusion-SS3D, a new perspective of enhancing the quality of pseudo-labels via the diffusion model for semi-supervised 3D object detection. Specifically, we include noises to produce corrupted 3D object size and class label distributions, and then utilize the diffusion model as a denoising process to obtain bounding box outputs. Moreover, we integrate the diffusion model into the teacher-student framework, so that the denoised bounding boxes can be used to improve pseudo-label generation, as well as the entire semi-supervised learning process. We conduct experiments on the ScanNet and SUN RGB-D benchmark datasets to demonstrate that our approach achieves state-of-the-art performance against existing methods. We also present extensive analysis to understand how our diffusion model design affects performance in semi-supervised learning.

Ji-Jia Wu, Andy Chia-Hao Chang, Chieh-Yu Chuang et al.

This paper addresses text-supervised semantic segmentation, aiming to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated that contrastive learning on image-text pairs effectively aligns visual segments with the meanings of texts. We notice that there is a discrepancy between text alignment and semantic segmentation: A text often consists of multiple semantic concepts, whereas semantic segmentation strives to create semantically homogeneous segments. To address this issue, we propose a novel framework, Image-Text Co-Decomposition (CoDe), where the paired image and text are jointly decomposed into a set of image regions and a set of word segments, respectively, and contrastive learning is developed to enforce region-word alignment. To work with a vision-language model, we present a prompt learning mechanism that derives an extra representation to highlight an image segment or a word segment of interest, with which more effective features can be extracted from that segment. Comprehensive experimental results demonstrate that our method performs favorably against existing text-supervised semantic segmentation methods on six benchmark datasets.

Chung-Ho Wu, Yang-Jung Chen, Ying-Huan Chen et al.

Three-dimensional scene inpainting is crucial for applications from virtual reality to architectural visualization, yet existing methods struggle with view consistency and geometric accuracy in 360° unbounded scenes. We present AuraFusion360, a novel reference-based method that enables high-quality object removal and hole filling in 3D scenes represented by Gaussian Splatting. Our approach introduces (1) depth-aware unseen mask generation for accurate occlusion identification, (2) Adaptive Guided Depth Diffusion, a zero-shot method for accurate initial point placement without requiring additional training, and (3) SDEdit-based detail enhancement for multi-view coherence. We also introduce 360-USID, the first comprehensive dataset for 360° unbounded scene inpainting with ground truth. Extensive experiments demonstrate that AuraFusion360 significantly outperforms existing methods, achieving superior perceptual quality while maintaining geometric accuracy across dramatic viewpoint changes.

Kuan-Hung Liu, Cheng-Kun Yang, Min-Hung Chen et al.

In the task of reference-based image inpainting, an additional reference image is provided to restore a damaged target image to its original state. The advancement of diffusion models, particularly Stable Diffusion, allows for simple formulations in this task. However, existing diffusion-based methods often lack explicit constraints on the correlation between the reference and damaged images, resulting in lower faithfulness to the reference images in the inpainting results. In this work, we propose CorrFill, a training-free module designed to enhance the awareness of geometric correlations between the reference and target images. This enhancement is achieved by guiding the inpainting process with correspondence constraints estimated during inpainting, utilizing attention masking in self-attention layers and an objective function to update the input tensor according to the constraints. Experimental results demonstrate that CorrFill significantly enhances the performance of multiple baseline diffusion-based methods, including state-of-the-art approaches, by emphasizing faithfulness to the reference images.

Chin-Yang Lin, Cheng Sun, Fu-En Yang et al. · nvidia

LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift, inaccurate geometry initialization, and severe memory limitations. To address these issues, we introduce LongSplat, a robust unposed 3D Gaussian Splatting framework featuring: (1) Incremental Joint Optimization that concurrently optimizes camera poses and 3D Gaussians to avoid local minima and ensure global consistency; (2) a robust Pose Estimation Module leveraging learned 3D priors; and (3) an efficient Octree Anchor Formation mechanism that converts dense point clouds into anchors based on spatial density. Extensive experiments on challenging benchmarks demonstrate that LongSplat achieves state-of-the-art results, substantially improving rendering quality, pose accuracy, and computational efficiency compared to prior approaches. Project page: https://linjohnss.github.io/longsplat/

Jui-Che Chiang, Hou-Ning Hu, Bo-Syuan Hou et al.

Although facial landmark detection (FLD) has gained significant progress, existing FLD methods still suffer from performance drops on partially non-visible faces, such as faces with occlusions or under extreme lighting conditions or poses. To address this issue, we introduce ORFormer, a novel transformer-based method that can detect non-visible regions and recover their missing features from visible parts. Specifically, ORFormer associates each image patch token with one additional learnable token called the messenger token. The messenger token aggregates features from all but its patch. This way, the consensus between a patch and other patches can be assessed by referring to the similarity between its regular and messenger embeddings, enabling non-visible region identification. Our method then recovers occluded patches with features aggregated by the messenger tokens. Leveraging the recovered features, ORFormer compiles high-quality heatmaps for the downstream FLD task. Extensive experiments show that our method generates heatmaps resilient to partial occlusions. By integrating the resultant heatmaps into existing FLD methods, our method performs favorably against the state of the arts on challenging datasets such as WFLW and COFW.

Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin et al.

Image dehazing aims to remove unwanted hazy artifacts in images. Although previous research has collected paired real-world hazy and haze-free images to improve dehazing models' performance in real-world scenarios, these models often experience significant performance drops when handling unseen real-world hazy images due to limited training data. This issue motivates us to develop a flexible domain adaptation method to enhance dehazing performance during testing. Observing that predicting haze patterns is generally easier than recovering clean content, we propose the Physics-guided Haze Transfer Network (PHATNet) which transfers haze patterns from unseen target domains to source-domain haze-free images, creating domain-specific fine-tuning sets to update dehazing models for effective domain adaptation. Additionally, we introduce a Haze-Transfer-Consistency loss and a Content-Leakage Loss to enhance PHATNet's disentanglement ability. Experimental results demonstrate that PHATNet significantly boosts state-of-the-art dehazing models on benchmark real-world image dehazing datasets.

Yu-Jen Tseng, Chia-Hao Kao, Jing-Zhong Chen et al.

We present the first unified framework for rate-distortion-optimized compression and segmentation of 3D Gaussian Splatting (3DGS). While 3DGS has proven effective for both real-time rendering and semantic scene understanding, prior works have largely treated these tasks independently, leaving their joint consideration unexplored. Inspired by recent advances in rate-distortion-optimized 3DGS compression, this work integrates semantic learning into the compression pipeline to support decoder-side applications--such as scene editing and manipulation--that extend beyond traditional scene reconstruction and view synthesis. Our scheme features a lightweight implicit neural representation-based hyperprior, enabling efficient entropy coding of both color and semantic attributes while avoiding costly grid-based hyperprior as seen in many prior works. To facilitate compression and segmentation, we further develop compression-guided segmentation learning, consisting of quantization-aware training to enhance feature separability and a quality-aware weighting mechanism to suppress unreliable Gaussian primitives. Extensive experiments on the LERF and 3D-OVS datasets demonstrate that our approach significantly reduces transmission cost while preserving high rendering quality and strong segmentation performance.

Fu-Jen Tsai, Yan-Tsung Peng, Chen-Yu Chang et al.

Video restoration is a low-level vision task that seeks to restore clean, sharp videos from quality-degraded frames. One would use the temporal information from adjacent frames to make video restoration successful. Recently, the success of the Transformer has raised awareness in the computer-vision community. However, its self-attention mechanism requires much memory, which is unsuitable for high-resolution vision tasks like video restoration. In this paper, we propose ViStripformer (Video Stripformer), which utilizes spatio-temporal strip attention to catch long-range data correlations, consisting of intra-frame strip attention (Intra-SA) and inter-frame strip attention (Inter-SA) for extracting spatial and temporal information. It decomposes video frames into strip-shaped features in horizontal and vertical directions for Intra-SA and Inter-SA to address degradation patterns with various orientations and magnitudes. Besides, ViStripformer is an effective and efficient transformer architecture with much lower memory usage than the vanilla transformer. Extensive experiments show that the proposed model achieves superior results with fast inference time on video restoration tasks, including video deblurring, demoireing, and deraining.

Yan-Bo Lin, Hung-Yu Tseng, Hsin-Ying Lee et al.

Sound localization aims to find the source of the audio signal in the visual scene. However, it is labor-intensive to annotate the correlations between the signals sampled from the audio and visual modalities, thus making it difficult to supervise the learning of a machine for this task. In this work, we propose an iterative contrastive learning framework that requires no data annotations. At each iteration, the proposed method takes the 1) localization results in images predicted in the previous iteration, and 2) semantic relationships inferred from the audio signals as the pseudo-labels. We then use the pseudo-labels to learn the correlation between the visual and audio signals sampled from the same video (intra-frame sampling) as well as the association between those extracted across videos (inter-frame relation). Our iterative strategy gradually encourages the localization of the sounding objects and reduces the correlation between the non-sounding regions and the reference audio. Quantitative and qualitative experimental results demonstrate that the proposed framework performs favorably against existing unsupervised and weakly-supervised methods on the sound localization task.

Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin et al.

Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform. Previous research attempted to solve non-uniform blurs using self-recurrent multiscale, multi-patch, or multi-temporal architectures with self-attention to obtain decent results. However, using self-recurrent frameworks typically lead to a longer inference time, while inter-pixel or inter-channel self-attention may cause excessive memory usage. This paper proposes a Blur-aware Attention Network (BANet), that accomplishes accurate and efficient deblurring via a single forward pass. Our BANet utilizes region-based self-attention with multi-kernel strip pooling to disentangle blur patterns of different magnitudes and orientations and cascaded parallel dilated convolution to aggregate multi-scale content features. Extensive experimental results on the GoPro and RealBlur benchmarks demonstrate that the proposed BANet performs favorably against the state-of-the-arts in blurred image restoration and can provide deblurred results in real-time.

Liangjian Chen, Shih-Yao Lin, Yusheng Xie et al.

Estimating 3D hand pose directly from RGB imagesis challenging but has gained steady progress recently bytraining deep models with annotated 3D poses. Howeverannotating 3D poses is difficult and as such only a few 3Dhand pose datasets are available, all with limited samplesizes. In this study, we propose a new framework of training3D pose estimation models from RGB images without usingexplicit 3D annotations, i.e., trained with only 2D informa-tion. Our framework is motivated by two observations: 1)Videos provide richer information for estimating 3D posesas opposed to static images; 2) Estimated 3D poses oughtto be consistent whether the videos are viewed in the for-ward order or reverse order. We leverage these two obser-vations to develop a self-supervised learning model calledtemporal-aware self-supervised network (TASSN). By en-forcing temporal consistency constraints, TASSN learns 3Dhand poses and meshes from videos with only 2D keypointposition annotations. Experiments show that our modelachieves surprisingly good results, with 3D estimation ac-curacy on par with the state-of-the-art models trained with3D annotations, highlighting the benefit of the temporalconsistency in constraining 3D prediction models.

Liangjian Chen, Shih-Yao Lin, Yusheng Xie et al.

Estimating3D hand poses from RGB images is essentialto a wide range of potential applications, but is challengingowing to substantial ambiguity in the inference of depth in-formation from RGB images. State-of-the-art estimators ad-dress this problem by regularizing3D hand pose estimationmodels during training to enforce the consistency betweenthe predicted3D poses and the ground-truth depth maps.However, these estimators rely on both RGB images and thepaired depth maps during training. In this study, we proposea conditional generative adversarial network (GAN) model,called Depth-image Guided GAN (DGGAN), to generate re-alistic depth maps conditioned on the input RGB image, anduse the synthesized depth maps to regularize the3D handpose estimation model, therefore eliminating the need forground-truth depth maps. Experimental results on multiplebenchmark datasets show that the synthesized depth mapsproduced by DGGAN are quite effective in regularizing thepose estimation model, yielding new state-of-the-art resultsin estimation accuracy, notably reducing the mean3D end-point errors (EPE) by4.7%,16.5%, and6.8%on the RHD,STB and MHP datasets, respectively.

Cheng-Chun Hsu, Yi-Hsuan Tsai, Yen-Yu Lin et al.

A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds. Most existing methods adopt feature alignment either on the image level or instance level. However, image-level alignment on global features may tangle foreground/background pixels at the same time, while instance-level alignment using proposals may suffer from the background noise. Different from existing solutions, we propose a domain adaptation framework that accounts for each pixel via predicting pixel-wise objectness and centerness. Specifically, the proposed method carries out center-aware alignment by paying more attention to foreground pixels, hence achieving better adaptation across domains. We demonstrate our method on numerous adaptation settings with extensive experimental results and show favorable performance against existing state-of-the-art algorithms.

Hung-Yu Tseng, Yi-Wen Chen, Yi-Hsuan Tsai et al.

With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinforcement learning, and domain generalization. However, meta-learning models are prone to overfitting when there are no sufficient training tasks for the meta-learners to generalize. Although existing approaches such as Dropout are widely used to address the overfitting problem, these methods are typically designed for regularizing models of a single task in supervised training. In this paper, we introduce a simple yet effective method to alleviate the risk of overfitting for gradient-based meta-learning. Specifically, during the gradient-based adaptation stage, we randomly drop the gradient in the inner-loop optimization of each parameter in deep neural networks, such that the augmented gradients improve generalization to new tasks. We present a general form of the proposed gradient dropout regularization and show that this term can be sampled from either the Bernoulli or Gaussian distribution. To validate the proposed method, we conduct extensive experiments and analysis on numerous computer vision tasks, demonstrating that the gradient dropout regularization mitigates the overfitting problem and improves the performance upon various gradient-based meta-learning frameworks.

Yun-Chun Chen, Po-Hsiang Huang, Li-Yu Yu et al.

Establishing dense semantic correspondences between object instances remains a challenging problem due to background clutter, significant scale and pose differences, and large intra-class variations. In this paper, we address weakly supervised semantic matching based on a deep network where only image pairs without manual keypoint correspondence annotations are provided. To facilitate network training with this weaker form of supervision, we 1) explicitly estimate the foreground regions to suppress the effect of background clutter and 2) develop cycle-consistent losses to enforce the predicted transformations across multiple images to be geometrically plausible and consistent. We train the proposed model using the PF-PASCAL dataset and evaluate the performance on the PF-PASCAL, PF-WILLOW, and TSS datasets. Extensive experimental results show that the proposed approach performs favorably against the state-of-the-art methods.

Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin et al.

Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade re-ID performance in real-world scenarios. To overcome this problem, we propose a novel generative adversarial network to address cross-resolution person re-ID, allowing query images with varying resolutions. By advancing adversarial learning techniques, our proposed model learns resolution-invariant image representations while being able to recover the missing details in low-resolution input images. The resulting features can be jointly applied for improving re-ID performance due to preserving resolution invariance and recovering re-ID oriented discriminative details. Extensive experimental results on five standard person re-ID benchmarks confirm the effectiveness of our method and the superiority over the state-of-the-art approaches, especially when the input resolutions are not seen during training. Furthermore, the experimental results on two vehicle re-ID benchmarks also confirm the generalization of our model on cross-resolution visual tasks. The extensions of semi-supervised settings further support the use of our proposed approach to real-world scenarios and applications.

Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang et al.

Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e.g., synthetic to real images). The adapted representations often do not capture pixel-level domain shifts that are crucial for dense prediction tasks (e.g., semantic segmentation). In this paper, we present a novel pixel-wise adversarial domain adaptation algorithm. By leveraging image-to-image translation methods for data augmentation, our key insight is that while the translated images between domains may differ in styles, their predictions for the task should be consistent. We exploit this property and introduce a cross-domain consistency loss that enforces our adapted model to produce consistent predictions. Through extensive experimental results, we show that our method compares favorably against the state-of-the-art on a wide variety of unsupervised domain adaptation tasks.

Yi-Wen Chen, Yi-Hsuan Tsai, Tiantian Wang et al.

Referring expressions are natural language descriptions that identify a particular object within a scene and are widely used in our daily conversations. In this work, we focus on segmenting the object in an image specified by a referring expression. To this end, we propose an end-to-end trainable comprehension network that consists of the language and visual encoders to extract feature representations from both domains. We introduce the spatial-aware dynamic filters to transfer knowledge from text to image, and effectively capture the spatial information of the specified object. To better communicate between the language and visual modules, we employ a caption generation network that takes features shared across both domains as input, and improves both representations via a consistency that enforces the generated sentence to be similar to the given referring expression. We evaluate the proposed framework on two referring expression datasets and show that our method performs favorably against the state-of-the-art algorithms.

Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin et al.

Person re-identification (re-ID) aims at matching images of the same identity across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade person re-ID performance in real-world scenarios. To overcome this problem, we propose a novel generative adversarial network to address cross-resolution person re-ID, allowing query images with varying resolutions. By advancing adversarial learning techniques, our proposed model learns resolution-invariant image representations while being able to recover the missing details in low-resolution input images. The resulting features can be jointly applied for improving person re-ID performance due to preserving resolution invariance and recovering re-ID oriented discriminative details. Our experiments on five benchmark datasets confirm the effectiveness of our approach and its superiority over the state-of-the-art methods, especially when the input resolutions are unseen during training.

Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang et al.

We present an approach for jointly matching and segmenting object instances of the same category within a collection of images. In contrast to existing algorithms that tackle the tasks of semantic matching and object co-segmentation in isolation, our method exploits the complementary nature of the two tasks. The key insights of our method are two-fold. First, the estimated dense correspondence fields from semantic matching provide supervision for object co-segmentation by enforcing consistency between the predicted masks from a pair of images. Second, the predicted object masks from object co-segmentation in turn allow us to reduce the adverse effects due to background clutters for improving semantic matching. Our model is end-to-end trainable and does not require supervision from manually annotated correspondences and object masks. We validate the efficacy of our approach on five benchmark datasets: TSS, Internet, PF-PASCAL, PF-WILLOW, and SPair-71k, and show that our algorithm performs favorably against the state-of-the-art methods on both semantic matching and object co-segmentation tasks.

Yi-Wen Chen, Yi-Hsuan Tsai, Chu-Ya Yang et al.

In order to learn object segmentation models in videos, conventional methods require a large amount of pixel-wise ground truth annotations. However, collecting such supervised data is time-consuming and labor-intensive. In this paper, we exploit existing annotations in source images and transfer such visual information to segment videos with unseen object categories. Without using any annotations in the target video, we propose a method to jointly mine useful segments and learn feature representations that better adapt to the target frames. The entire process is decomposed into two tasks: 1) solving a submodular function for selecting object-like segments, and 2) learning a CNN model with a transferable module for adapting seen categories in the source domain to the unseen target video. We present an iterative update scheme between two tasks to self-learn the final solution for object segmentation. Experimental results on numerous benchmark datasets show that the proposed method performs favorably against the state-of-the-art algorithms.

Shih-Yao Lin, Yen-Yu Lin, Chu-Song Chen et al.

This paper aims at recognizing partially observed human actions in videos. Action videos acquired in uncontrolled environments often contain corrupt frames, which make actions partially observed. Furthermore, these frames can last for arbitrary lengths of time and appear irregularly. They are inconsistent with training data and degrade the performance of pre-trained action recognition systems. We present an approach to address this issue. For each training and testing actions, we divide it into segments and explore the mutual dependency between temporal segments. This property states that the similarity of two actions at one segment often implies their similarity at another. We augment each segment with extra alternatives retrieved from training data. The augmentation algorithm is designed in a way where a few alternatives are good enough to replace the original segment where corrupt frames occur. Our approach is developed upon hidden conditional random fields and leverages the flexibility of hidden variables for uncertainty handling. It turns out that our approach integrates corrupt segment detection and alternative selection into the process of prediction, and can recognize partially observed actions more accurately. It is evaluated on both fully observed actions and partially observed ones with either synthetic or real corrupt frames. The experimental results manifest its general applicability and superior performance, especially when corrupt frames are present in the action videos.

Liangjian Chen, Shih-Yao Lin, Yusheng Xie et al.

Hand pose estimation from a monocular RGB image is an important but challenging task. The main factor affecting its performance is the lack of a sufficiently large training dataset with accurate hand-keypoint annotations. In this work, we circumvent this problem by proposing an effective method for generating realistic hand poses and show that state-of-the-art algorithms for hand pose estimation can be greatly improved by utilizing the generated hand poses as training data. Specifically, we first adopt an augmented reality (AR) simulator to synthesize hand poses with accurate hand-keypoint labels. Although the synthetic hand poses come with precise joint labels, eliminating the need of manual annotations, they look unnatural and are not the ideal training data. To produce more realistic hand poses, we propose to blend a synthetic hand pose with a real background, such as arms and sleeves. To this end, we develop tonality-alignment generative adversarial networks (TAGANs), which align the tonality and color distributions between synthetic hand poses and real backgrounds, and can generate high quality hand poses. We evaluate TAGAN on three benchmarks, including the RHP, STB, and CMU-PS hand pose datasets. With the aid of the synthesized poses, our method performs favorably against the state-of-the-arts in both 2D and 3D hand pose estimations.

Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou et al.

We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground truth segmentation distribution with the consideration of the spatial resolution. We show that the proposed discriminator can be used to improve semantic segmentation accuracy by coupling the adversarial loss with the standard cross entropy loss of the proposed model. In addition, the fully convolutional discriminator enables semi-supervised learning through discovering the trustworthy regions in predicted results of unlabeled images, thereby providing additional supervisory signals. In contrast to existing methods that utilize weakly-labeled images, our method leverages unlabeled images to enhance the segmentation model. Experimental results on the PASCAL VOC 2012 and Cityscapes datasets demonstrate the effectiveness of the proposed algorithm.

Yuan-Ting Hu, Yen-Yu Lin, Hsin-Yi Chen et al.

With the aim to improve the performance of feature matching, we present an unsupervised approach to fuse various local descriptors in the space of homographies. Inspired by the observation that the homographies of correct feature correspondences vary smoothly along the spatial domain, our approach stands on the unsupervised nature of feature matching, and can select a good descriptor for matching each feature point. Specifically, the homography space serves as the common domain, in which a correspondence obtained by any descriptor is considered as a point, for integrating various heterogeneous descriptors. Both geometric coherence and spatial continuity among correspondences are considered via computing their geodesic distances in the space. In this way, mutual verification across different descriptors is allowed, and correct correspondences will be highlighted with a high degree of consistency (i.e., short geodesic distances here). It follows that one-class SVM can be applied to identifying these correct correspondences, and boosts the performance of feature matching. The proposed approach is comprehensively compared with the state-of-the-art approaches, and evaluated on four benchmarks of image matching. The promising results manifest its effectiveness.