Ming-Hsuan Yang

Yunhao Ge, Jie Ren, Andrew Gallagher et al. · deepmind

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of these models are very high, the top-1 accuracies are much lower (over 25% gap in some cases). We investigate the reasons for this performance gap and find that many of the failure cases are caused by ambiguity in the text prompts. First, we develop a simple and efficient zero-shot post-hoc method to identify images whose top-1 prediction is likely to be incorrect, by measuring consistency of the predictions w.r.t. multiple prompts and image transformations. We show that our procedure better predicts mistakes, outperforming the popular max logit baseline on selective prediction tasks. Next, we propose a simple and efficient way to improve accuracy on such uncertain images by making use of the WordNet hierarchy; specifically we augment the original class by incorporating its parent and children from the semantic label hierarchy, and plug the augmentation into text prompts. We conduct experiments on both CLIP and LiT models with five different ImageNet-based datasets. For CLIP, our method improves the top-1 accuracy by 17.13% on the uncertain subset and 3.6% on the entire ImageNet validation set. We also show that our method improves across ImageNet shifted datasets, four other datasets, and other model architectures such as LiT. The proposed method is hyperparameter-free, requires no additional model training and can be easily scaled to other large multi-modal architectures. Code is available at https://github.com/gyhandy/Hierarchy-CLIP.

Ling Yang, Zhilong Zhang, Yang Song et al.

Diffusion models have emerged as a powerful new family of deep generative models with record-breaking performance in many applications, including image synthesis, video generation, and molecule design. In this survey, we provide an overview of the rapidly expanding body of work on diffusion models, categorizing the research into three key areas: efficient sampling, improved likelihood estimation, and handling data with special structures. We also discuss the potential for combining diffusion models with other generative models for enhanced results. We further review the wide-ranging applications of diffusion models in fields spanning from computer vision, natural language generation, temporal data modeling, to interdisciplinary applications in other scientific disciplines. This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration. Github: https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy.

Huiwen Chang, Han Zhang, Jarred Barber et al. · deepmind

We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens. Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding. The use of a pre-trained LLM enables fine-grained language understanding, translating to high-fidelity image generation and the understanding of visual concepts such as objects, their spatial relationships, pose, cardinality etc. Our 900M parameter model achieves a new SOTA on CC3M, with an FID score of 6.06. The Muse 3B parameter model achieves an FID of 7.88 on zero-shot COCO evaluation, along with a CLIP score of 0.32. Muse also directly enables a number of image editing applications without the need to fine-tune or invert the model: inpainting, outpainting, and mask-free editing. More results are available at https://muse-model.github.io

Syed Waqas Zamir, Aditya Arora, Salman Khan et al.

Given a degraded input image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous vehicles, and remote sensing. Significant advances in image restoration have been made in recent years, dominated by convolutional neural networks (CNNs). The widely-used CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former case, spatial details are preserved but the contextual information cannot be precisely encoded. In the latter case, generated outputs are semantically reliable but spatially less accurate. This paper presents a new architecture with a holistic goal of maintaining spatially-precise high-resolution representations through the entire network, and receiving complementary contextual information from the low-resolution representations. The core of our approach is a multi-scale residual block containing the following key elements: (a) parallel multi-resolution convolution streams for extracting multi-scale features, (b) information exchange across the multi-resolution streams, (c) non-local attention mechanism for capturing contextual information, and (d) attention based multi-scale feature aggregation. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Extensive experiments on six real image benchmark datasets demonstrate that our method, named as MIRNet-v2 , achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement. The source code and pre-trained models are available at https://github.com/swz30/MIRNetv2

Liangzhe Yuan, Nitesh Bharadwaj Gundavarapu, Long Zhao et al. · deepmind

We evaluate the video understanding capabilities of existing foundation models (FMs) using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition,temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring an FM for downstream tasks. Furthermore, we jointly profile FMs' efficacy and efficiency when adapting to general video understanding tasks using cost measurements during both training and inference. Our main findings areas follows. First, task-specialized models significantly outperform the seven FMs studied in this work, in sharp contrast to what FMs have achieved in natural language and image understanding. Second, video-native FMs, whose pretraining data mainly contains the video modality, are generally better than image-native FMs in classifying motion-rich videos, localizing actions in time, and understanding a video of more than one action. Third, the video-native FMs can perform well on video tasks under light adaptations to downstream tasks (e.g., freezing the FM backbones), while image-native FMs win in full end-to-end finetuning. The first two observations reveal the need and tremendous opportunities to conduct research on video-focused FMs, and the last confirms that both tasks and adaptation methods matter when it comes to the evaluation of FMs. Our code is released under: https://github.com/tensorflow/models/tree/master/official/projects/videoglue.

Muhammad Uzair Khattak, Syed Talal Wasim, Muzammal Naseer et al.

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. Conventionally trained using the task-specific objective, i.e., cross-entropy loss, prompts tend to overfit downstream data distributions and find it challenging to capture task-agnostic general features from the frozen CLIP. This leads to the loss of the model's original generalization capability. To address this issue, our work introduces a self-regularization framework for prompting called PromptSRC (Prompting with Self-regulating Constraints). PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations using a three-pronged approach by: (a) regulating prompted representations via mutual agreement maximization with the frozen model, (b) regulating with self-ensemble of prompts over the training trajectory to encode their complementary strengths, and (c) regulating with textual diversity to mitigate sample diversity imbalance with the visual branch. To the best of our knowledge, this is the first regularization framework for prompt learning that avoids overfitting by jointly attending to pre-trained model features, the training trajectory during prompting, and the textual diversity. PromptSRC explicitly steers the prompts to learn a representation space that maximizes performance on downstream tasks without compromising CLIP generalization. We perform extensive experiments on 4 benchmarks where PromptSRC overall performs favorably well compared to the existing methods. Our code and pre-trained models are publicly available at: https://github.com/muzairkhattak/PromptSRC.

Abdelrahman Shaker, Muhammad Maaz, Hanoona Rasheed et al.

Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks. Within the transformer models, the self-attention mechanism is one of the main building blocks that strives to capture long-range dependencies. However, the self-attention operation has quadratic complexity which proves to be a computational bottleneck, especially in volumetric medical imaging, where the inputs are 3D with numerous slices. In this paper, we propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features using a pair of inter-dependent branches based on spatial and channel attention. Our spatial attention formulation is efficient having linear complexity with respect to the input sequence length. To enable communication between spatial and channel-focused branches, we share the weights of query and key mapping functions that provide a complimentary benefit (paired attention), while also reducing the overall network parameters. Our extensive evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy. On Synapse, our UNETR++ sets a new state-of-the-art with a Dice Score of 87.2%, while being significantly efficient with a reduction of over 71% in terms of both parameters and FLOPs, compared to the best method in the literature. Code: https://github.com/Amshaker/unetr_plus_plus.

Runsheng Xu, Hao Xiang, Zhengzhong Tu et al.

In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present a robust cooperative perception framework with V2X communication using a novel vision Transformer. Specifically, we build a holistic attention model, namely V2X-ViT, to effectively fuse information across on-road agents (i.e., vehicles and infrastructure). V2X-ViT consists of alternating layers of heterogeneous multi-agent self-attention and multi-scale window self-attention, which captures inter-agent interaction and per-agent spatial relationships. These key modules are designed in a unified Transformer architecture to handle common V2X challenges, including asynchronous information sharing, pose errors, and heterogeneity of V2X components. To validate our approach, we create a large-scale V2X perception dataset using CARLA and OpenCDA. Extensive experimental results demonstrate that V2X-ViT sets new state-of-the-art performance for 3D object detection and achieves robust performance even under harsh, noisy environments. The code is available at https://github.com/DerrickXuNu/v2x-vit.

Abdelrahman Shaker, Muhammad Maaz, Hanoona Rasheed et al.

Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially for deployment on resource-constrained mobile devices. Although hybrid approaches have been proposed to combine the advantages of convolutions and self-attention for a better speed-accuracy trade-off, the expensive matrix multiplication operations in self-attention remain a bottleneck. In this work, we introduce a novel efficient additive attention mechanism that effectively replaces the quadratic matrix multiplication operations with linear element-wise multiplications. Our design shows that the key-value interaction can be replaced with a linear layer without sacrificing any accuracy. Unlike previous state-of-the-art methods, our efficient formulation of self-attention enables its usage at all stages of the network. Using our proposed efficient additive attention, we build a series of models called "SwiftFormer" which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed. Our small variant achieves 78.5% top-1 ImageNet-1K accuracy with only 0.8 ms latency on iPhone 14, which is more accurate and 2x faster compared to MobileViT-v2. Code: https://github.com/Amshaker/SwiftFormer

Lijun Yu, Yong Cheng, Kihyuk Sohn et al. · cmu, deepmind

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.

Muhammad Awais, Muzammal Naseer, Salman Khan et al.

Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world environment can be better described in human language, naturally governed by grammatical rules and other modalities such as audio and depth. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. These models are referred to as foundational models. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions. In this survey, we provide a comprehensive review of such emerging foundational models, including typical architecture designs to combine different modalities (vision, text, audio, etc), training objectives (contrastive, generative), pre-training datasets, fine-tuning mechanisms, and the common prompting patterns; textual, visual, and heterogeneous. We discuss the open challenges and research directions for foundational models in computer vision, including difficulties in their evaluations and benchmarking, gaps in their real-world understanding, limitations of their contextual understanding, biases, vulnerability to adversarial attacks, and interpretability issues. We review recent developments in this field, covering a wide range of applications of foundation models systematically and comprehensively. A comprehensive list of foundational models studied in this work is available at \url{https://github.com/awaisrauf/Awesome-CV-Foundational-Models}.

Lijun Yu, José Lezama, Nitesh B. Gundavarapu et al. · cmu, deepmind

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.

Akshay Dudhane, Syed Waqas Zamir, Salman Khan et al.

On a shutter press, modern handheld cameras capture multiple images in rapid succession and merge them to generate a single image. However, individual frames in a burst are misaligned due to inevitable motions and contain multiple degradations. The challenge is to properly align the successive image shots and merge their complimentary information to achieve high-quality outputs. Towards this direction, we propose Burstormer: a novel transformer-based architecture for burst image restoration and enhancement. In comparison to existing works, our approach exploits multi-scale local and non-local features to achieve improved alignment and feature fusion. Our key idea is to enable inter-frame communication in the burst neighborhoods for information aggregation and progressive fusion while modeling the burst-wide context. However, the input burst frames need to be properly aligned before fusing their information. Therefore, we propose an enhanced deformable alignment module for aligning burst features with regards to the reference frame. Unlike existing methods, the proposed alignment module not only aligns burst features but also exchanges feature information and maintains focused communication with the reference frame through the proposed reference-based feature enrichment mechanism, which facilitates handling complex motions. After multi-level alignment and enrichment, we re-emphasize on inter-frame communication within burst using a cyclic burst sampling module. Finally, the inter-frame information is aggregated using the proposed burst feature fusion module followed by progressive upsampling. Our Burstormer outperforms state-of-the-art methods on burst super-resolution, burst denoising and burst low-light enhancement. Our codes and pretrained models are available at https:// github.com/akshaydudhane16/Burstormer

Jean Lahoud, Jiale Cao, Fahad Shahbaz Khan et al.

The success of the transformer architecture in natural language processing has recently triggered attention in the computer vision field. The transformer has been used as a replacement for the widely used convolution operators, due to its ability to learn long-range dependencies. This replacement was proven to be successful in numerous tasks, in which several state-of-the-art methods rely on transformers for better learning. In computer vision, the 3D field has also witnessed an increase in employing the transformer for 3D convolution neural networks and multi-layer perceptron networks. Although a number of surveys have focused on transformers in vision in general, 3D vision requires special attention due to the difference in data representation and processing when compared to 2D vision. In this work, we present a systematic and thorough review of more than 100 transformers methods for different 3D vision tasks, including classification, segmentation, detection, completion, pose estimation, and others. We discuss transformer design in 3D vision, which allows it to process data with various 3D representations. For each application, we highlight key properties and contributions of proposed transformer-based methods. To assess the competitiveness of these methods, we compare their performance to common non-transformer methods on 12 3D benchmarks. We conclude the survey by discussing different open directions and challenges for transformers in 3D vision. In addition to the presented papers, we aim to frequently update the latest relevant papers along with their corresponding implementations at: https://github.com/lahoud/3d-vision-transformers.

Ling Yang, Zhilin Huang, Yang Song et al.

Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images. Most existing methods address this challenge by using scene layouts, which are image-like representations of scene graphs designed to capture the coarse structures of scene images. Because scene layouts are manually crafted, the alignment with images may not be fully optimized, causing suboptimal compliance between the generated images and the original scene graphs. To tackle this issue, we propose to learn scene graph embeddings by directly optimizing their alignment with images. Specifically, we pre-train an encoder to extract both global and local information from scene graphs that are predictive of the corresponding images, relying on two loss functions: masked autoencoding loss and contrastive loss. The former trains embeddings by reconstructing randomly masked image regions, while the latter trains embeddings to discriminate between compliant and non-compliant images according to the scene graph. Given these embeddings, we build a latent diffusion model to generate images from scene graphs. The resulting method, called SGDiff, allows for the semantic manipulation of generated images by modifying scene graph nodes and connections. On the Visual Genome and COCO-Stuff datasets, we demonstrate that SGDiff outperforms state-of-the-art methods, as measured by both the Inception Score and Fréchet Inception Distance (FID) metrics. We will release our source code and trained models at https://github.com/YangLing0818/SGDiff.

Hsin-Ping Huang, Deqing Sun, Yaojie Liu et al. · deepmind

While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust performance. In this paper, we present adaptive vision transformers (ViT) for robust cross-domain face antispoofing. Specifically, we adopt ViT as a backbone to exploit its strength to account for long-range dependencies among pixels. We further introduce the ensemble adapters module and feature-wise transformation layers in the ViT to adapt to different domains for robust performance with a few samples. Experiments on several benchmark datasets show that the proposed models achieve both robust and competitive performance against the state-of-the-art methods for cross-domain face anti-spoofing using a few samples.

Zhiwei Lin, Tingting Liang, Taihong Xiao et al. · pku

Existing optical flow estimators usually employ the network architectures typically designed for image classification as the encoder to extract per-pixel features. However, due to the natural difference between the tasks, the architectures designed for image classification may be sub-optimal for flow estimation. To address this issue, we propose a neural architecture search method named FlowNAS to automatically find the better encoder architecture for flow estimation task. We first design a suitable search space including various convolutional operators and construct a weight-sharing super-network for efficiently evaluating the candidate architectures. Then, for better training the super-network, we propose Feature Alignment Distillation, which utilizes a well-trained flow estimator to guide the training of super-network. Finally, a resource-constrained evolutionary algorithm is exploited to find an optimal architecture (i.e., sub-network). Experimental results show that the discovered architecture with the weights inherited from the super-network achieves 4.67\% F1-all error on KITTI, an 8.4\% reduction of RAFT baseline, surpassing state-of-the-art handcrafted models GMA and AGFlow, while reducing the model complexity and latency. The source code and trained models will be released in https://github.com/VDIGPKU/FlowNAS.

Chun-Han Yao, Jimei Yang, Duygu Ceylan et al.

Estimating 3D human pose and shape from 2D images is a crucial yet challenging task. While prior methods with model-based representations can perform reasonably well on whole-body images, they often fail when parts of the body are occluded or outside the frame. Moreover, these results usually do not faithfully capture the human silhouettes due to their limited representation power of deformable models (e.g., representing only the naked body). An alternative approach is to estimate dense vertices of a predefined template body in the image space. Such representations are effective in localizing vertices within an image but cannot handle out-of-frame body parts. In this work, we learn dense human body estimation that is robust to partial observations. We explicitly model the visibility of human joints and vertices in the x, y, and z axes separately. The visibility in x and y axes help distinguishing out-of-frame cases, and the visibility in depth axis corresponds to occlusions (either self-occlusions or occlusions by other objects). We obtain pseudo ground-truths of visibility labels from dense UV correspondences and train a neural network to predict visibility along with 3D coordinates. We show that visibility can serve as 1) an additional signal to resolve depth ordering ambiguities of self-occluded vertices and 2) a regularization term when fitting a human body model to the predictions. Extensive experiments on multiple 3D human datasets demonstrate that visibility modeling significantly improves the accuracy of human body estimation, especially for partial-body cases. Our project page with code is at: https://github.com/chhankyao/visdb.

Kuan-Chih Huang, Ming-Hsuan Yang, Yi-Hsuan Tsai

Recent advances of monocular 3D object detection facilitate the 3D multi-object tracking task based on low-cost camera sensors. In this paper, we find that the motion cue of objects along different time frames is critical in 3D multi-object tracking, which is less explored in existing monocular-based approaches. In this paper, we propose a motion-aware framework for monocular 3D MOT. To this end, we propose MoMA-M3T, a framework that mainly consists of three motion-aware components. First, we represent the possible movement of an object related to all object tracklets in the feature space as its motion features. Then, we further model the historical object tracklet along the time frame in a spatial-temporal perspective via a motion transformer. Finally, we propose a motion-aware matching module to associate historical object tracklets and current observations as final tracking results. We conduct extensive experiments on the nuScenes and KITTI datasets to demonstrate that our MoMA-M3T achieves competitive performance against state-of-the-art methods. Moreover, the proposed tracker is flexible and can be easily plugged into existing image-based 3D object detectors without re-training. Code and models are available at https://github.com/kuanchihhuang/MoMA-M3T.

Xiangtai Li, Shilin Xu, Yibo Yang et al.

Panoptic Part Segmentation (PPS) unifies panoptic and part segmentation into one task. Previous works utilize separate approaches to handle things, stuff, and part predictions without shared computation and task association. We aim to unify these tasks at the architectural level, designing the first end-to-end unified framework, Panoptic-PartFormer. Moreover, we find the previous metric PartPQ biases to PQ. To handle both issues, we first design a meta-architecture that decouples part features and things/stuff features, respectively. We model things, stuff, and parts as object queries and directly learn to optimize all three forms of prediction as a unified mask prediction and classification problem. We term our model as Panoptic-PartFormer. Second, we propose a new metric Part-Whole Quality (PWQ), better to measure this task from pixel-region and part-whole perspectives. It also decouples the errors for part segmentation and panoptic segmentation. Third, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross-attention scheme to boost part segmentation qualities further. We design a new part-whole interaction method using masked cross attention. Finally, extensive ablation studies and analysis demonstrate the effectiveness of both Panoptic-PartFormer and Panoptic-PartFormer++. Compared with previous Panoptic-PartFormer, our Panoptic-PartFormer++ achieves 2% PartPQ and 3% PWQ improvements on the Cityscapes PPS dataset and 5% PartPQ on the Pascal Context PPS dataset. On both datasets, Panoptic-PartFormer++ achieves new state-of-the-art results. Our models can serve as a strong baseline and aid future research in PPS. The source code and trained models will be available at~\url{https://github.com/lxtGH/Panoptic-PartFormer}.

Hwanjun Song, Deqing Sun, Sanghyuk Chun et al.

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully transformer-based architecture for image classification. In this paper, we integrate Vision and Detection Transformers (ViDT) to construct an effective and efficient object detector. ViDT introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector, followed by a computationally efficient transformer decoder that exploits multi-scale features and auxiliary techniques essential to boost the detection performance without much increase in computational load. In addition, we extend it to ViDT+ to support joint-task learning for object detection and instance segmentation. Specifically, we attach an efficient multi-scale feature fusion layer and utilize two more auxiliary training losses, IoU-aware loss and token labeling loss. Extensive evaluation results on the Microsoft COCO benchmark dataset demonstrate that ViDT obtains the best AP and latency trade-off among existing fully transformer-based object detectors, and its extended ViDT+ achieves 53.2AP owing to its high scalability for large models. The source code and trained models are available at https://github.com/naver-ai/vidt.

Lijun Yu, Yong Cheng, Zhiruo Wang et al. · cmu, deepmind

In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs to perform both understanding and generation tasks involving non-linguistic modalities such as images or videos. SPAE converts between raw pixels and interpretable lexical tokens (or words) extracted from the LLM's vocabulary. The resulting tokens capture both the semantic meaning and the fine-grained details needed for visual reconstruction, effectively translating the visual content into a language comprehensible to the LLM, and empowering it to perform a wide array of multimodal tasks. Our approach is validated through in-context learning experiments with frozen PaLM 2 and GPT 3.5 on a diverse set of image understanding and generation tasks. Our method marks the first successful attempt to enable a frozen LLM to generate image content while surpassing state-of-the-art performance in image understanding tasks, under the same setting, by over 25%.

Qi Li, Weining Wang, Chengzhong Xu et al.

Although face swapping has attracted much attention in recent years, it remains a challenging problem. Existing methods leverage a large number of data samples to explore the intrinsic properties of face swapping without considering the semantic information of face images. Moreover, the representation of the identity information tends to be fixed, leading to suboptimal face swapping. In this paper, we present a simple yet efficient method named FaceSwapper, for one-shot face swapping based on Generative Adversarial Networks. Our method consists of a disentangled representation module and a semantic-guided fusion module. The disentangled representation module comprises an attribute encoder and an identity encoder, which aims to achieve the disentanglement of the identity and attribute information. The identity encoder is more flexible, and the attribute encoder contains more attribute details than its competitors. Benefiting from the disentangled representation, FaceSwapper can swap face images progressively. In addition, semantic information is introduced into the semantic-guided fusion module to control the swapped region and model the pose and expression more accurately. Experimental results show that our method achieves state-of-the-art results on benchmark datasets with fewer training samples. Our code is publicly available at https://github.com/liqi-casia/FaceSwapper.

Yunhao Ge, Yuecheng Li, Shuo Ni et al.

Continual learning aims to emulate the human ability to continually accumulate knowledge over sequential tasks. The main challenge is to maintain performance on previously learned tasks after learning new tasks, i.e., to avoid catastrophic forgetting. We propose a Channel-wise Lightweight Reprogramming (CLR) approach that helps convolutional neural networks (CNNs) overcome catastrophic forgetting during continual learning. We show that a CNN model trained on an old task (or self-supervised proxy task) could be ``reprogrammed" to solve a new task by using our proposed lightweight (very cheap) reprogramming parameter. With the help of CLR, we have a better stability-plasticity trade-off to solve continual learning problems: To maintain stability and retain previous task ability, we use a common task-agnostic immutable part as the shared ``anchor" parameter set. We then add task-specific lightweight reprogramming parameters to reinterpret the outputs of the immutable parts, to enable plasticity and integrate new knowledge. To learn sequential tasks, we only train the lightweight reprogramming parameters to learn each new task. Reprogramming parameters are task-specific and exclusive to each task, which makes our method immune to catastrophic forgetting. To minimize the parameter requirement of reprogramming to learn new tasks, we make reprogramming lightweight by only adjusting essential kernels and learning channel-wise linear mappings from anchor parameters to task-specific domain knowledge. We show that, for general CNNs, the CLR parameter increase is less than 0.6\% for any new task. Our method outperforms 13 state-of-the-art continual learning baselines on a new challenging sequence of 53 image classification datasets. Code and data are available at https://github.com/gyhandy/Channel-wise-Lightweight-Reprogramming

Amandeep Kumar, Ankan Kumar Bhunia, Sanath Narayan et al.

We present a method to efficiently generate 3D-aware high-resolution images that are view-consistent across multiple target views. The proposed multiplane neural radiance model, named GMNR, consists of a novel α-guided view-dependent representation (α-VdR) module for learning view-dependent information. The α-VdR module, faciliated by an α-guided pixel sampling technique, computes the view-dependent representation efficiently by learning viewing direction and position coefficients. Moreover, we propose a view-consistency loss to enforce photometric similarity across multiple views. The GMNR model can generate 3D-aware high-resolution images that are viewconsistent across multiple camera poses, while maintaining the computational efficiency in terms of both training and inference time. Experiments on three datasets demonstrate the effectiveness of the proposed modules, leading to favorable results in terms of both generation quality and inference time, compared to existing approaches. Our GMNR model generates 3D-aware images of 1024 X 1024 pixels with 17.6 FPS on a single V100. Code : https://github.com/VIROBO-15/GMNR

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.

Fangzhou Lin, Peiran Li, Lingyu Xu et al.

Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edits and do not fully capture the diversity of real-image tasks in professional workflows. Here, we define instructional computer vision problem solving as a broader formulation of image editing: given a real input image and a natural-language instruction, a system must produce an edited output that realizes the requested transformation while satisfying explicit preservation, geometric, physical, and usability constraints. We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales. CV-Arena contains 12K high-resolution real-image instruction pairs spanning 16 instruction-based visual task types, constructed using CogRetriever, a dual-track retrieval-and-curation pipeline that combines targeted web search, agentic query refinement, verification, and traceability. To evaluate models at scale while preserving human fidelity, we propose Active Elo, a human-AI collaborative preference protocol that leverages CV-Judge, a logic-gated, multi-dimensional VLM evaluator, to reject clear failures and resolve high-confidence comparisons; and to route close, high-quality comparisons to expert raters. Mixed human and AI supervision is then aggregated through reliability-weighted Elo updates. Our comprehensive evaluation of 21 systems, including proprietary, open-source, and agentic models, on CV-Arena reveals persistent gaps in instruction adherence, physical reasoning, structural control, and fine-grained detail preservation. We further develop CV-Agent, a lightweight agentic model that combines planning, editing, and verification, and demonstrate that closed-loop reasoning is a promising direction for professional-grade instruction-following visual editing.

Long Zhao, Liangzhe Yuan, Boqing Gong et al. · deepmind

This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. Merging labels spanning different datasets could be challenging due to inconsistent taxonomies. The issue is exacerbated in visual relationship detection when second-order visual semantics are introduced between pairs of objects. To address this challenge, we propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models (VLMs). VLMs provide well-aligned image and text embeddings, where similar relationships are optimized to be close to each other for semantic unification. Our bottom-up design enables the model to enjoy the benefit of training with both object detection and visual relationship datasets. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model. UniVRD achieves 38.07 mAP on HICO-DET, outperforming the current best bottom-up HOI detector by 14.26 mAP. More importantly, we show that our unified detector performs as well as dataset-specific models in mAP, and achieves further improvements when we scale up the model. Our code will be made publicly available on GitHub.

Yue Han, Jiangning Zhang, Yabiao Wang et al.

Few-Shot Instance Segmentation (FSIS) requires detecting and segmenting novel classes with limited support examples. Existing methods based on Region Proposal Networks (RPNs) face two issues: 1) Overfitting suppresses novel class objects; 2) Dual-branch models require complex spatial correlation strategies to prevent spatial information loss when generating class prototypes. We introduce a unified framework, Reference Twice (RefT), to exploit the relationship between support and query features for FSIS and related tasks. Our three main contributions are: 1) A novel transformer-based baseline that avoids overfitting, offering a new direction for FSIS; 2) Demonstrating that support object queries encode key factors after base training, allowing query features to be enhanced twice at both feature and query levels using simple cross-attention, thus avoiding complex spatial correlation interaction; 3) Introducing a class-enhanced base knowledge distillation loss to address the issue of DETR-like models struggling with incremental settings due to the input projection layer, enabling easy extension to incremental FSIS. Extensive experimental evaluations on the COCO dataset under three FSIS settings demonstrate that our method performs favorably against existing approaches across different shots, \eg, $+8.2/+9.4$ performance gain over state-of-the-art methods with 10/30-shots. Source code and models will be available at https://github.com/hanyue1648/RefT.

Shuangkang Fang, Yufeng Wang, Yi-Hsuan Tsai et al.

Recent work on image content manipulation based on vision-language pre-training models has been effectively extended to text-driven 3D scene editing. However, existing schemes for 3D scene editing still exhibit certain shortcomings, hindering their further interactive design. Such schemes typically adhere to fixed input patterns, limiting users' flexibility in text input. Moreover, their editing capabilities are constrained by a single or a few 2D visual models and require intricate pipeline design to integrate these models into 3D reconstruction processes. To address the aforementioned issues, we propose a dialogue-based 3D scene editing approach, termed CE3D, which is centered around a large language model that allows for arbitrary textual input from users and interprets their intentions, subsequently facilitating the autonomous invocation of the corresponding visual expert models. Furthermore, we design a scheme utilizing Hash-Atlas to represent 3D scene views, which transfers the editing of 3D scenes onto 2D atlas images. This design achieves complete decoupling between the 2D editing and 3D reconstruction processes, enabling CE3D to flexibly integrate a wide range of existing 2D or 3D visual models without necessitating intricate fusion designs. Experimental results demonstrate that CE3D effectively integrates multiple visual models to achieve diverse editing visual effects, possessing strong scene comprehension and multi-round dialog capabilities. The code is available at https://sk-fun.fun/CE3D.

Meng Liu, Mingda Zhang, Jialu Liu et al.

In this paper, we present a novel problem, namely video timeline modeling. Our objective is to create a video-associated timeline from a set of videos related to a specific topic, thereby facilitating the content and structure understanding of the story being told. This problem has significant potential in various real-world applications, for instance, news story summarization. To bootstrap research in this area, we curate a realistic benchmark dataset, YouTube-News-Timeline, consisting of over $12$k timelines and $300$k YouTube news videos. Additionally, we propose a set of quantitative metrics to comprehensively evaluate and compare methodologies. With such a testbed, we further develop and benchmark several deep learning approaches to tackling this problem. We anticipate that this exploratory work will pave the way for further research in video timeline modeling. The assets are available via https://github.com/google-research/google-research/tree/master/video_timeline_modeling.

Zhiwei Lin, Yongtao Wang, Shengxiang Qi et al.

Existing LiDAR-based 3D object detection methods for autonomous driving scenarios mainly adopt the training-from-scratch paradigm. Unfortunately, this paradigm heavily relies on large-scale labeled data, whose collection can be expensive and time-consuming. Self-supervised pre-training is an effective and desirable way to alleviate this dependence on extensive annotated data. In this work, we present BEV-MAE, an efficient masked autoencoder pre-training framework for LiDAR-based 3D object detection in autonomous driving. Specifically, we propose a bird's eye view (BEV) guided masking strategy to guide the 3D encoder learning feature representation in a BEV perspective and avoid complex decoder design during pre-training. Furthermore, we introduce a learnable point token to maintain a consistent receptive field size of the 3D encoder with fine-tuning for masked point cloud inputs. Based on the property of outdoor point clouds in autonomous driving scenarios, i.e., the point clouds of distant objects are more sparse, we propose point density prediction to enable the 3D encoder to learn location information, which is essential for object detection. Experimental results show that BEV-MAE surpasses prior state-of-the-art self-supervised methods and achieves a favorably pre-training efficiency. Furthermore, based on TransFusion-L, BEV-MAE achieves new state-of-the-art LiDAR-based 3D object detection results, with 73.6 NDS and 69.6 mAP on the nuScenes benchmark. The source code will be released at https://github.com/VDIGPKU/BEV-MAE

Lu Qi, Jason Kuen, Weidong Guo et al.

Dense image segmentation tasks e.g., semantic, panoptic) are useful for image editing, but existing methods can hardly generalize well in an in-the-wild setting where there are unrestricted image domains, classes, and image resolution and quality variations. Motivated by these observations, we construct a new entity segmentation dataset, with a strong focus on high-quality dense segmentation in the wild. The dataset contains images spanning diverse image domains and entities, along with plentiful high-resolution images and high-quality mask annotations for training and testing. Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images. It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image. CropFormer is the first query-based Transformer architecture that can effectively fuse mask predictions from multiple image views, by learning queries that effectively associate the same entities across the full image and its crop. With CropFormer, we achieve a significant AP gain of $1.9$ on the challenging entity segmentation task. Furthermore, CropFormer consistently improves the accuracy of traditional segmentation tasks and datasets. The dataset and code will be released at http://luqi.info/entityv2.github.io/.

Taihong Xiao, Zirui Wang, Liangliang Cao et al. · cmu

Vision-language foundation models pretrained on large-scale data provide a powerful tool for many visual understanding tasks. Notably, many vision-language models build two encoders (visual and textual) that can map two modalities into the same embedding space. As a result, the learned representations achieve good zero-shot performance on tasks like image classification. However, when there are only a few examples per category, the potential of large vision-language models is often underperformed, mainly due to the gap between a large number of parameters and a relatively small amount of training data. This paper shows that we can significantly improve the performance of few-shot classification by using the category names to initialize the classification head. With the proposed category name initialization method, our model obtains the state-of-the-art performance on a number of few-shot image classification benchmarks (e.g., 87.37% on ImageNet and 96.08% on Stanford Cars, both using five-shot learning).

Xin Li, Yuqing Huang, Zhenyu He et al.

Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking. However, a single image patch cannot provide a complete and precise concept of the target object as images are limited in their ability to abstract and can be ambiguous, which makes it difficult to track targets with drastic variations. In this paper, we propose the CiteTracker to enhance target modeling and inference in visual tracking by connecting images and text. Specifically, we develop a text generation module to convert the target image patch into a descriptive text containing its class and attribute information, providing a comprehensive reference point for the target. In addition, a dynamic description module is designed to adapt to target variations for more effective target representation. We then associate the target description and the search image using an attention-based correlation module to generate the correlated features for target state reference. Extensive experiments on five diverse datasets are conducted to evaluate the proposed algorithm and the favorable performance against the state-of-the-art methods demonstrates the effectiveness of the proposed tracking method.

Chen Zhang, Guorong Li, Yuankai Qi et al.

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and self-refining anomaly scores with these labels. As the pseudo labels play a crucial role, we propose an enhancement framework by exploiting completeness and uncertainty properties for effective self-training. Specifically, we first design a multi-head classification module (each head serves as a classifier) with a diversity loss to maximize the distribution differences of predicted pseudo labels across heads. This encourages the generated pseudo labels to cover as many abnormal events as possible. We then devise an iterative uncertainty pseudo label refinement strategy, which improves not only the initial pseudo labels but also the updated ones obtained by the desired classifier in the second stage. Extensive experimental results demonstrate the proposed method performs favorably against state-of-the-art approaches on the UCF-Crime, TAD, and XD-Violence benchmark datasets.

Yuanhao Xiong, Long Zhao, Boqing Gong et al. · deepmind

Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information in both videos and text, which is of importance to downstream tasks requiring temporal localization and semantic reasoning. A powerful model is expected to be capable of capturing region-object correspondences and recognizing scene changes in a video clip, reflecting spatial and temporal granularity, respectively. To strengthen model's understanding into such fine-grained details, we propose a simple yet effective video-language modeling framework, S-ViLM, by exploiting the intrinsic structures of these two modalities. It includes two novel designs, inter-clip spatial grounding and intra-clip temporal grouping, to promote learning region-object alignment and temporal-aware features, simultaneously. Comprehensive evaluations demonstrate that S-ViLM performs favorably against existing approaches in learning more expressive representations. Specifically, S-ViLM surpasses the state-of-the-art methods substantially on four representative downstream tasks, covering text-video retrieval, video question answering, video action recognition, and temporal action localization.

Yuheng Liu, Xinke Li, Xueting Li et al.

Diffusion models have shown remarkable results in generating 2D images and small-scale 3D objects. However, their application to the synthesis of large-scale 3D scenes has been rarely explored. This is mainly due to the inherent complexity and bulky size of 3D scenery data, particularly outdoor scenes, and the limited availability of comprehensive real-world datasets, which makes training a stable scene diffusion model challenging. In this work, we explore how to effectively generate large-scale 3D scenes using the coarse-to-fine paradigm. We introduce a framework, the Pyramid Discrete Diffusion model (PDD), which employs scale-varied diffusion models to progressively generate high-quality outdoor scenes. Experimental results of PDD demonstrate our successful exploration in generating 3D scenes both unconditionally and conditionally. We further showcase the data compatibility of the PDD model, due to its multi-scale architecture: a PDD model trained on one dataset can be easily fine-tuned with another dataset. Code is available at https://github.com/yuhengliu02/pyramid-discrete-diffusion.

Chun-Han Yao, Wei-Chih Hung, Yuanzhen Li et al.

Automatically estimating 3D skeleton, shape, camera viewpoints, and part articulation from sparse in-the-wild image ensembles is a severely under-constrained and challenging problem. Most prior methods rely on large-scale image datasets, dense temporal correspondence, or human annotations like camera pose, 2D keypoints, and shape templates. We propose Hi-LASSIE, which performs 3D articulated reconstruction from only 20-30 online images in the wild without any user-defined shape or skeleton templates. We follow the recent work of LASSIE that tackles a similar problem setting and make two significant advances. First, instead of relying on a manually annotated 3D skeleton, we automatically estimate a class-specific skeleton from the selected reference image. Second, we improve the shape reconstructions with novel instance-specific optimization strategies that allow reconstructions to faithful fit on each instance while preserving the class-specific priors learned across all images. Experiments on in-the-wild image ensembles show that Hi-LASSIE obtains higher fidelity state-of-the-art 3D reconstructions despite requiring minimum user input.

Hanoona Rasheed, Muhammad Maaz, Sahal Shaji Mullappilly et al.

Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded responses. However, they are limited to only referring to a single object category at a time, require users to specify the regions, or cannot offer dense pixel-wise object grounding. In this work, we present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentation masks. GLaMM not only grounds objects appearing in the conversations but is flexible enough to accept both textual and optional visual prompts (region of interest) as input. This empowers users to interact with the model at various levels of granularity, both in textual and visual domains. Due to the lack of standard benchmarks for the novel setting of visually Grounded Conversation Generation (GCG), we introduce a comprehensive evaluation protocol with our curated grounded conversations. Our proposed GCG task requires densely grounded concepts in natural scenes at a large-scale. To this end, we propose a densely annotated Grounding-anything Dataset (GranD) using our proposed automated annotation pipeline that encompasses 7.5M unique concepts grounded in a total of 810M regions available with segmentation masks. Besides GCG, GLaMM also performs effectively on several downstream tasks, e.g., referring expression segmentation, image and region-level captioning and vision-language conversations.

Chieh Hubert Lin, Hsin-Ying Lee, Willi Menapace et al.

Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises. InfiniCity decomposes the seemingly impractical task into three feasible modules, taking advantage of both 2D and 3D data. First, an infinite-pixel image synthesis module generates arbitrary-scale 2D maps from the bird's-eye view. Next, an octree-based voxel completion module lifts the generated 2D map to 3D octrees. Finally, a voxel-based neural rendering module texturizes the voxels and renders 2D images. InfiniCity can thus synthesize arbitrary-scale and traversable 3D city environments, and allow flexible and interactive editing from users. We quantitatively and qualitatively demonstrate the efficacy of the proposed framework. Project page: https://hubert0527.github.io/infinicity/

Christoph Mayer, Martin Danelljan, Ming-Hsuan Yang et al.

Generic Object Tracking (GOT) is the problem of tracking target objects, specified by bounding boxes in the first frame of a video. While the task has received much attention in the last decades, researchers have almost exclusively focused on the single object setting. Multi-object GOT benefits from a wider applicability, rendering it more attractive in real-world applications. We attribute the lack of research interest into this problem to the absence of suitable benchmarks. In this work, we introduce a new large-scale GOT benchmark, LaGOT, containing multiple annotated target objects per sequence. Our benchmark allows users to tackle key remaining challenges in GOT, aiming to increase robustness and reduce computation through joint tracking of multiple objects simultaneously. In addition, we propose a transformer-based GOT tracker baseline capable of joint processing of multiple objects through shared computation. Our approach achieves a 4x faster run-time in case of 10 concurrent objects compared to tracking each object independently and outperforms existing single object trackers on our new benchmark. In addition, our approach achieves highly competitive results on single-object GOT datasets, setting a new state of the art on TrackingNet with a success rate AUC of 84.4%. Our benchmark, code, and trained models will be made publicly available.

Gaoxiang Cong, Liang Li, Yuankai Qi et al.

Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference. V2C is more challenging than conventional text-to-speech tasks as it additionally requires the generated speech to exactly match the varying emotions and speaking speed presented in the video. Unlike previous works, we propose a novel movie dubbing architecture to tackle these problems via hierarchical prosody modelling, which bridges the visual information to corresponding speech prosody from three aspects: lip, face, and scene. Specifically, we align lip movement to the speech duration, and convey facial expression to speech energy and pitch via attention mechanism based on valence and arousal representations inspired by recent psychology findings. Moreover, we design an emotion booster to capture the atmosphere from global video scenes. All these embeddings together are used to generate mel-spectrogram and then convert to speech waves via existing vocoder. Extensive experimental results on the Chem and V2C benchmark datasets demonstrate the favorable performance of the proposed method. The source code and trained models will be released to the public.

Qi Li, Weining Wang, Shuangjun Du et al.

Face swapping has witnessed significant progress in recent years, largely driven by advances in deep generative models such as GANs and diffusion models.Despite these advances, existing methods remain fragmented across different paradigms, and their evaluation is highly inconsistent due to the lack of standardized datasets and protocols. Moreover, prior surveys primarily focus on broader deepfake generation or detection, leaving face swapping insufficiently studied as a standalone problem. In this paper, we present a comprehensive survey and benchmark for face swapping. We provide a structured review of existing methods, organizing them into five major paradigms and systematically analyzing their design principles, strengths, and limitations. To enable fair and controlled evaluation, we introduce CASIA FaceSwapping, a high-quality benchmark with balanced demographic distributions and explicit attribute variations, and establish standardized protocols to assess the robustness of different face swapping methods. Extensive experiments on representative approaches yield new insights into the performance characteristics and limitations of current techniques. Overall, our work provides a unified perspective and a principled evaluation framework to facilitate the development of more robust and controllable face swapping methods. More results can be found at https://github.com/CASIA-NLPRAI/face-swapping-survey.

Ziheng Yan, Yuankai Qi, Guorong Li et al.

Crowd counting is usually handled in a density map regression fashion, which is supervised via a L2 loss between the predicted density map and ground truth. To effectively regulate models, various improved L2 loss functions have been proposed to find a better correspondence between predicted density and annotation positions. In this paper, we propose to predict the density map at one resolution but measure the density map at multiple resolutions. By maximizing the posterior probability in such a setting, we obtain a log-formed multi-resolution L2-difference loss, where the traditional single-resolution L2 loss is its particular case. We mathematically prove it is superior to a single-resolution L2 loss. Without bells and whistles, the proposed loss substantially improves several baselines and performs favorably compared to state-of-the-art methods on four crowd counting datasets, ShanghaiTech A & B, UCF-QNRF, and JHU-Crowd++.

Xinyan Liu, Guorong Li, Yuankai Qi et al.

Crowd localization aims to predict the spatial position of humans in a crowd scenario. We observe that the performance of existing methods is challenged from two aspects: (i) ranking inconsistency between test and training phases; and (ii) fixed anchor resolution may underfit or overfit crowd densities of local regions. To address these problems, we design a supervision target reassignment strategy for training to reduce ranking inconsistency and propose an anchor pyramid scheme to adaptively determine the anchor density in each image region. Extensive experimental results on three widely adopted datasets (ShanghaiTech A\&B, JHU-CROWD++, UCF-QNRF) demonstrate the favorable performance against several state-of-the-art methods.

Jixuan He, Xueting Li, Chieh Hubert Lin et al.

Vision-Language Models (VLMs) exhibit emerging spatial reasoning capabilities, yet they remain unreliable on tasks requiring precise spatial understanding, such as viewpoint reasoning, directional comparison, and distance estimation. In multi-view images and monocular videos, relevant spatial cues are often sparse and distributed across redundant observations, making them difficult to organize and exploit. Reconstruction-based Vision Foundation Models (VFMs) offer a natural way to aggregate such observations into explicit spatial memory, such as point clouds. However, simply exposing reconstruction models as free-form tools is brittle, VLMs may invoke tools incorrectly, skip required spatial transformations, or misuse intermediate results. We propose \textbf{Reasmory}, a framework that formulates spatial reasoning as structured program execution over reconstructed spatial memory. Reasmory constructs explicit 3D memory, augments it with semantically grounded 3D object instances, and introduces a lightweight Domain-Specific Language (DSL) that constrains how VLMs query objects and cameras, transform viewpoints, and render observations during reasoning. Generated programs are parsed and validated before execution, enabling more reliable interaction with spatial memory than unconstrained tool use. Experiments on multi-view image and video spatial reasoning benchmarks show consistent gains of 6--18\% over strong baselines, including GPT-5-mini and Gemini-3-flash, indicating that explicit 3D memory is most useful when accessed through constrained, validated operations rather than free-form tool calls.

Tiantian Wang, Nikolaos Sarafianos, Ming-Hsuan Yang et al.

We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Despite the significant progress recently on this topic, with several methods exploring shared canonical neural radiance fields in dynamic scene scenarios, learning a user-controlled model for unseen poses remains a challenging task. To tackle this problem, we introduce an effective method to a) integrate observations across several frames and b) encode the appearance at each individual frame. We accomplish this by utilizing both the human pose that models the body shape as well as point clouds that partially cover the human as input. Our approach simultaneously learns a shared set of latent codes anchored to the human pose among several frames, and an appearance-dependent code anchored to incomplete point clouds generated by each frame and its predicted depth. The former human pose-based code models the shape of the performer whereas the latter point cloud-based code predicts fine-level details and reasons about missing structures at the unseen poses. To further recover non-visible regions in query frames, we employ a temporal transformer to integrate features of points in query frames and tracked body points from automatically-selected key frames. Experiments on various sequences of dynamic humans from different datasets including ZJU-MoCap show that our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input.

Junyi Zhang, Charles Herrmann, Junhwa Hur et al.

While pre-trained large-scale vision models have shown significant promise for semantic correspondence, their features often struggle to grasp the geometry and orientation of instances. This paper identifies the importance of being geometry-aware for semantic correspondence and reveals a limitation of the features of current foundation models under simple post-processing. We show that incorporating this information can markedly enhance semantic correspondence performance with simple but effective solutions in both zero-shot and supervised settings. We also construct a new challenging benchmark for semantic correspondence built from an existing animal pose estimation dataset, for both pre-training validating models. Our method achieves a PCK@0.10 score of 65.4 (zero-shot) and 85.6 (supervised) on the challenging SPair-71k dataset, outperforming the state of the art by 5.5p and 11.0p absolute gains, respectively. Our code and datasets are publicly available at: https://telling-left-from-right.github.io/.

Chun-Han Yao, Wei-Chih Hung, Yuanzhen Li et al.

Creating high-quality articulated 3D models of animals is challenging either via manual creation or using 3D scanning tools. Therefore, techniques to reconstruct articulated 3D objects from 2D images are crucial and highly useful. In this work, we propose a practical problem setting to estimate 3D pose and shape of animals given only a few (10-30) in-the-wild images of a particular animal species (say, horse). Contrary to existing works that rely on pre-defined template shapes, we do not assume any form of 2D or 3D ground-truth annotations, nor do we leverage any multi-view or temporal information. Moreover, each input image ensemble can contain animal instances with varying poses, backgrounds, illuminations, and textures. Our key insight is that 3D parts have much simpler shape compared to the overall animal and that they are robust w.r.t. animal pose articulations. Following these insights, we propose LASSIE, a novel optimization framework which discovers 3D parts in a self-supervised manner with minimal user intervention. A key driving force behind LASSIE is the enforcing of 2D-3D part consistency using self-supervisory deep features. Experiments on Pascal-Part and self-collected in-the-wild animal datasets demonstrate considerably better 3D reconstructions as well as both 2D and 3D part discovery compared to prior arts. Project page: chhankyao.github.io/lassie/