Fatih Porikli

Hanzhe Hu, Yinbo Chen, Jiarui Xu et al.

Integrating high-level context information with low-level details is of central importance in semantic segmentation. Towards this end, most existing segmentation models apply bilinear up-sampling and convolutions to feature maps of different scales, and then align them at the same resolution. However, bilinear up-sampling blurs the precise information learned in these feature maps and convolutions incur extra computation costs. To address these issues, we propose the Implicit Feature Alignment function (IFA). Our method is inspired by the rapidly expanding topic of implicit neural representations, where coordinate-based neural networks are used to designate fields of signals. In IFA, feature vectors are viewed as representing a 2D field of information. Given a query coordinate, nearby feature vectors with their relative coordinates are taken from the multi-level feature maps and then fed into an MLP to generate the corresponding output. As such, IFA implicitly aligns the feature maps at different levels and is capable of producing segmentation maps in arbitrary resolutions. We demonstrate the efficacy of IFA on multiple datasets, including Cityscapes, PASCAL Context, and ADE20K. Our method can be combined with improvement on various architectures, and it achieves state-of-the-art computation-accuracy trade-off on common benchmarks. Code will be made available at https://github.com/hzhupku/IFA.

Rui Zhu, Zhengqin Li, Janarbek Matai et al.

Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible and invisible light sources require reasoning about long-range interactions for inverse rendering, which seeks to recover the components of image formation, namely, shape, material, and lighting. In this work, our intuition is that the long-range attention learned by transformer architectures is ideally suited to solve longstanding challenges in single-image inverse rendering. We demonstrate with a specific instantiation of a dense vision transformer, IRISformer, that excels at both single-task and multi-task reasoning required for inverse rendering. Specifically, we propose a transformer architecture to simultaneously estimate depths, normals, spatially-varying albedo, roughness and lighting from a single image of an indoor scene. Our extensive evaluations on benchmark datasets demonstrate state-of-the-art results on each of the above tasks, enabling applications like object insertion and material editing in a single unconstrained real image, with greater photorealism than prior works. Code and data are publicly released at https://github.com/ViLab-UCSD/IRISformer.

Liwen Wu, Rui Zhu, Mustafa B. Yaldiz et al.

Inverse path tracing has recently been applied to joint material and lighting estimation, given geometry and multi-view HDR observations of an indoor scene. However, it has two major limitations: path tracing is expensive to compute, and ambiguities exist between reflection and emission. Our Factorized Inverse Path Tracing (FIPT) addresses these challenges by using a factored light transport formulation and finds emitters driven by rendering errors. Our algorithm enables accurate material and lighting optimization faster than previous work, and is more effective at resolving ambiguities. The exhaustive experiments on synthetic scenes show that our method (1) outperforms state-of-the-art indoor inverse rendering and relighting methods particularly in the presence of complex illumination effects; (2) speeds up inverse path tracing optimization to less than an hour. We further demonstrate robustness to noisy inputs through material and lighting estimates that allow plausible relighting in a real scene. The source code is available at: https://github.com/lwwu2/fipt

Guillaume Berger, Manik Dhingra, Antoine Mercier et al. · cmu, stanford

In this work, we present QuickSRNet, an efficient super-resolution architecture for real-time applications on mobile platforms. Super-resolution clarifies, sharpens, and upscales an image to higher resolution. Applications such as gaming and video playback along with the ever-improving display capabilities of TVs, smartphones, and VR headsets are driving the need for efficient upscaling solutions. While existing deep learning-based super-resolution approaches achieve impressive results in terms of visual quality, enabling real-time DL-based super-resolution on mobile devices with compute, thermal, and power constraints is challenging. To address these challenges, we propose QuickSRNet, a simple yet effective architecture that provides better accuracy-to-latency trade-offs than existing neural architectures for single-image super resolution. We present training tricks to speed up existing residual-based super-resolution architectures while maintaining robustness to quantization. Our proposed architecture produces 1080p outputs via 2x upscaling in 2.2 ms on a modern smartphone, making it ideal for high-fps real-time applications.

Antoine Mercier, Ruan Erasmus, Yashesh Savani et al. · cmu, stanford

Real-time rendering for video games has become increasingly challenging due to the need for higher resolutions, framerates and photorealism. Supersampling has emerged as an effective solution to address this challenge. Our work introduces a novel neural algorithm for supersampling rendered content that is 4 times more efficient than existing methods while maintaining the same level of accuracy. Additionally, we introduce a new dataset which provides auxiliary modalities such as motion vectors and depth generated using graphics rendering features like viewport jittering and mipmap biasing at different resolutions. We believe that this dataset fills a gap in the current dataset landscape and can serve as a valuable resource to help measure progress in the field and advance the state-of-the-art in super-resolution techniques for gaming content.

Minghua Liu, Yinhao Zhu, Hong Cai et al.

Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets with fine-grained part annotations, which are costly to collect. This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection. We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm. We also utilize multi-view 3D priors and few-shot prompt tuning to boost performance significantly. Extensive evaluation on PartNet and PartNet-Mobility datasets shows that our method enables excellent zero-shot 3D part segmentation. Our few-shot version not only outperforms existing few-shot approaches by a large margin but also achieves highly competitive results compared to the fully supervised counterpart. Furthermore, we demonstrate that our method can be directly applied to iPhone-scanned point clouds without significant domain gaps.

Moloud Abdar, Meenakshi Kollati, Swaraja Kuraparthi et al.

Video captioning (VC) is a fast-moving, cross-disciplinary area of research that bridges work in the fields of computer vision, natural language processing (NLP), linguistics, and human-computer interaction. In essence, VC involves understanding a video and describing it with language. Captioning is used in a host of applications from creating more accessible interfaces (e.g., low-vision navigation) to video question answering (V-QA), video retrieval and content generation. This survey covers deep learning-based VC, including but, not limited to, attention-based architectures, graph networks, reinforcement learning, adversarial networks, dense video captioning (DVC), and more. We discuss the datasets and evaluation metrics used in the field, and limitations, applications, challenges, and future directions for VC.

Xingping Dong, Jianbing Shen, Fatih Porikli et al.

In this paper, we provide an intuitive viewing to simplify the Siamese-based trackers by converting the tracking task to a classification. Under this viewing, we perform an in-depth analysis for them through visual simulations and real tracking examples, and find that the failure cases in some challenging situations can be regarded as the issue of missing decisive samples in offline training. Since the samples in the initial (first) frame contain rich sequence-specific information, we can regard them as the decisive samples to represent the whole sequence. To quickly adapt the base model to new scenes, a compact latent network is presented via fully using these decisive samples. Specifically, we present a statistics-based compact latent feature for fast adjustment by efficiently extracting the sequence-specific information. Furthermore, a new diverse sample mining strategy is designed for training to further improve the discrimination ability of the proposed compact latent network. Finally, a conditional updating strategy is proposed to efficiently update the basic models to handle scene variation during the tracking phase. To evaluate the generalization ability and effectiveness and of our method, we apply it to adjust three classical Siamese-based trackers, namely SiamRPN++, SiamFC, and SiamBAN. Extensive experimental results on six recent datasets demonstrate that all three adjusted trackers obtain the superior performance in terms of the accuracy, while having high running speed.

Shubhankar Borse, Senthil Yogamani, Marvin Klingner et al.

Bird's-eye-view (BEV) grid is a typical representation of the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras only to perform segmentation in BEV space, which is fundamentally constrained by the absence of reliable depth information. The latest works leverage both camera and LiDAR modalities but suboptimally fuse their features using simple, concatenation-based mechanisms. In this paper, we address these problems by enhancing the alignment of the unimodal features in order to aid feature fusion, as well as enhancing the alignment between the cameras' perspective view (PV) and BEV representations. We propose X-Align, a novel end-to-end cross-modal and cross-view learning framework for BEV segmentation consisting of the following components: (i) a novel Cross-Modal Feature Alignment (X-FA) loss, (ii) an attention-based Cross-Modal Feature Fusion (X-FF) module to align multi-modal BEV features implicitly, and (iii) an auxiliary PV segmentation branch with Cross-View Segmentation Alignment (X-SA) losses to improve the PV-to-BEV transformation. We evaluate our proposed method across two commonly used benchmark datasets, i.e., nuScenes and KITTI-360. Notably, X-Align significantly outperforms the state-of-the-art by 3 absolute mIoU points on nuScenes. We also provide extensive ablation studies to demonstrate the effectiveness of the individual components.

Shubhankar Borse, Marvin Klingner, Varun Ravi Kumar et al.

Bird's-eye-view (BEV) grid is a common representation for the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras only to perform segmentation in BEV space, which is fundamentally constrained by the absence of reliable depth information. Latest works leverage both camera and LiDAR modalities, but sub-optimally fuse their features using simple, concatenation-based mechanisms. In this paper, we address these problems by enhancing the alignment of the unimodal features in order to aid feature fusion, as well as enhancing the alignment between the cameras' perspective view (PV) and BEV representations. We propose X-Align, a novel end-to-end cross-modal and cross-view learning framework for BEV segmentation consisting of the following components: (i) a novel Cross-Modal Feature Alignment (X-FA) loss, (ii) an attention-based Cross-Modal Feature Fusion (X-FF) module to align multi-modal BEV features implicitly, and (iii) an auxiliary PV segmentation branch with Cross-View Segmentation Alignment (X-SA) losses to improve the PV-to-BEV transformation. We evaluate our proposed method across two commonly used benchmark datasets, i.e., nuScenes and KITTI-360. Notably, X-Align significantly outperforms the state-of-the-art by 3 absolute mIoU points on nuScenes. We also provide extensive ablation studies to demonstrate the effectiveness of the individual components.

Jisoo Jeong, Jamie Menjay Lin, Fatih Porikli et al.

Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem where labels from real-world data are very challenging to derive. More specifically, we propose occlusion consistency and zero forcing in the forms of self-supervised learning and transformation consistency in the form of semi-supervised learning. We apply these consistency techniques in a way that the network model learns to describe pixel-level motions better while requiring no additional annotations. We demonstrate that our consistency strategies applied to a strong baseline network model using the original datasets and labels provide further improvements, attaining the state-of-the-art results on the KITTI-2015 scene flow benchmark in the non-stereo category. Our method achieves the best foreground accuracy (4.33% in Fl-all) over both the stereo and non-stereo categories, even though using only monocular image inputs.

Marvin Klingner, Shubhankar Borse, Varun Ravi Kumar et al.

Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera images underperform due to the necessary view transformation of features from perspective view (PV) to a 3D world representation which is ambiguous due to missing depth information. This paper introduces X$^3$KD, a comprehensive knowledge distillation framework across different modalities, tasks, and stages for multi-camera 3DOD. Specifically, we propose cross-task distillation from an instance segmentation teacher (X-IS) in the PV feature extraction stage providing supervision without ambiguous error backpropagation through the view transformation. After the transformation, we apply cross-modal feature distillation (X-FD) and adversarial training (X-AT) to improve the 3D world representation of multi-camera features through the information contained in a LiDAR-based 3DOD teacher. Finally, we also employ this teacher for cross-modal output distillation (X-OD), providing dense supervision at the prediction stage. We perform extensive ablations of knowledge distillation at different stages of multi-camera 3DOD. Our final X$^3$KD model outperforms previous state-of-the-art approaches on the nuScenes and Waymo datasets and generalizes to RADAR-based 3DOD. Qualitative results video at https://youtu.be/1do9DPFmr38.

Shashanka Venkataramanan, Amir Ghodrati, Yuki M. Asano et al.

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key redundancy that causes unnecessary computations. Based on this observation, we propose SkipAt, a method to reuse self-attention computation from preceding layers to approximate attention at one or more subsequent layers. To ensure that reusing self-attention blocks across layers does not degrade the performance, we introduce a simple parametric function, which outperforms the baseline transformer's performance while running computationally faster. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS. We achieve improved throughput at the same-or-higher accuracy levels in all these tasks.

Kaifeng Zhang, Yang Fu, Shubhankar Borse et al.

While 6D object pose estimation has wide applications across computer vision and robotics, it remains far from being solved due to the lack of annotations. The problem becomes even more challenging when moving to category-level 6D pose, which requires generalization to unseen instances. Current approaches are restricted by leveraging annotations from simulation or collected from humans. In this paper, we overcome this barrier by introducing a self-supervised learning approach trained directly on large-scale real-world object videos for category-level 6D pose estimation in the wild. Our framework reconstructs the canonical 3D shape of an object category and learns dense correspondences between input images and the canonical shape via surface embedding. For training, we propose novel geometrical cycle-consistency losses which construct cycles across 2D-3D spaces, across different instances and different time steps. The learned correspondence can be applied for 6D pose estimation and other downstream tasks such as keypoint transfer. Surprisingly, our method, without any human annotations or simulators, can achieve on-par or even better performance than previous supervised or semi-supervised methods on in-the-wild images. Our project page is: https://kywind.github.io/self-pose .

Rajeev Yasarla, Hong Cai, Jisoo Jeong et al.

We propose MAMo, a novel memory and attention frame-work for monocular video depth estimation. MAMo can augment and improve any single-image depth estimation networks into video depth estimation models, enabling them to take advantage of the temporal information to predict more accurate depth. In MAMo, we augment model with memory which aids the depth prediction as the model streams through the video. Specifically, the memory stores learned visual and displacement tokens of the previous time instances. This allows the depth network to cross-reference relevant features from the past when predicting depth on the current frame. We introduce a novel scheme to continuously update the memory, optimizing it to keep tokens that correspond with both the past and the present visual information. We adopt attention-based approach to process memory features where we first learn the spatio-temporal relation among the resultant visual and displacement memory tokens using self-attention module. Further, the output features of self-attention are aggregated with the current visual features through cross-attention. The cross-attended features are finally given to a decoder to predict depth on the current frame. Through extensive experiments on several benchmarks, including KITTI, NYU-Depth V2, and DDAD, we show that MAMo consistently improves monocular depth estimation networks and sets new state-of-the-art (SOTA) accuracy. Notably, our MAMo video depth estimation provides higher accuracy with lower latency, when omparing to SOTA cost-volume-based video depth models.

Yunxiao Shi, Hong Cai, Amin Ansari et al.

The ubiquitous multi-camera setup on modern autonomous vehicles provides an opportunity to construct surround-view depth. Existing methods, however, either perform independent monocular depth estimations on each camera or rely on computationally heavy self attention mechanisms. In this paper, we propose a novel guided attention architecture, EGA-Depth, which can improve both the efficiency and accuracy of self-supervised multi-camera depth estimation. More specifically, for each camera, we use its perspective view as the query to cross-reference its neighboring views to derive informative features for this camera view. This allows the model to perform attention only across views with considerable overlaps and avoid the costly computations of standard self-attention. Given its efficiency, EGA-Depth enables us to exploit higher-resolution visual features, leading to improved accuracy. Furthermore, EGA-Depth can incorporate more frames from previous time steps as it scales linearly w.r.t. the number of views and frames. Extensive experiments on two challenging autonomous driving benchmarks nuScenes and DDAD demonstrate the efficacy of our proposed EGA-Depth and show that it achieves the new state-of-the-art in self-supervised multi-camera depth estimation.

Minghan Zhu, Shizhong Han, Hong Cai et al.

In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation. 4D panoptic segmentation is a benchmark task for autonomous driving that requires recognizing semantic classes and object instances on the road based on LiDAR scans, as well as assigning temporally consistent IDs to instances across time. We observe that the driving scenario is symmetric to rotations on the ground plane. Therefore, rotation-equivariance could provide better generalization and more robust feature learning. Specifically, we review the object instance clustering strategies and restate the centerness-based approach and the offset-based approach as the prediction of invariant scalar fields and equivariant vector fields. Other sub-tasks are also unified from this perspective, and different invariant and equivariant layers are designed to facilitate their predictions. Through evaluation on the standard 4D panoptic segmentation benchmark of SemanticKITTI, we show that our equivariant models achieve higher accuracy with lower computational costs compared to their non-equivariant counterparts. Moreover, our method sets the new state-of-the-art performance and achieves 1st place on the SemanticKITTI 4D Panoptic Segmentation leaderboard.

Dushyant Mehta, Andrii Skliar, Haitam Ben Yahia et al.

Though the state-of-the architectures for semantic segmentation, such as HRNet, demonstrate impressive accuracy, the complexity arising from their salient design choices hinders a range of model acceleration tools, and further they make use of operations that are inefficient on current hardware. This paper demonstrates that a simple encoder-decoder architecture with a ResNet-like backbone and a small multi-scale head, performs on-par or better than complex semantic segmentation architectures such as HRNet, FANet and DDRNets. Naively applying deep backbones designed for Image Classification to the task of Semantic Segmentation leads to sub-par results, owing to a much smaller effective receptive field of these backbones. Implicit among the various design choices put forth in works like HRNet, DDRNet, and FANet are networks with a large effective receptive field. It is natural to ask if a simple encoder-decoder architecture would compare favorably if comprised of backbones that have a larger effective receptive field, though without the use of inefficient operations like dilated convolutions. We show that with minor and inexpensive modifications to ResNets, enlarging the receptive field, very simple and competitive baselines can be created for Semantic Segmentation. We present a family of such simple architectures for desktop as well as mobile targets, which match or exceed the performance of complex models on the Cityscapes dataset. We hope that our work provides simple yet effective baselines for practitioners to develop efficient semantic segmentation models.

Jisoo Jeong, Hong Cai, Risheek Garrepalli et al.

We propose a novel data augmentation approach, DistractFlow, for training optical flow estimation models by introducing realistic distractions to the input frames. Based on a mixing ratio, we combine one of the frames in the pair with a distractor image depicting a similar domain, which allows for inducing visual perturbations congruent with natural objects and scenes. We refer to such pairs as distracted pairs. Our intuition is that using semantically meaningful distractors enables the model to learn related variations and attain robustness against challenging deviations, compared to conventional augmentation schemes focusing only on low-level aspects and modifications. More specifically, in addition to the supervised loss computed between the estimated flow for the original pair and its ground-truth flow, we include a second supervised loss defined between the distracted pair's flow and the original pair's ground-truth flow, weighted with the same mixing ratio. Furthermore, when unlabeled data is available, we extend our augmentation approach to self-supervised settings through pseudo-labeling and cross-consistency regularization. Given an original pair and its distracted version, we enforce the estimated flow on the distracted pair to agree with the flow of the original pair. Our approach allows increasing the number of available training pairs significantly without requiring additional annotations. It is agnostic to the model architecture and can be applied to training any optical flow estimation models. Our extensive evaluations on multiple benchmarks, including Sintel, KITTI, and SlowFlow, show that DistractFlow improves existing models consistently, outperforming the latest state of the art.

Babak Ehteshami Bejnordi, Amirhossein Habibian, Fatih Porikli et al.

High-resolution images are widely adopted for high-performance object detection in videos. However, processing high-resolution inputs comes with high computation costs, and naive down-sampling of the input to reduce the computation costs quickly degrades the detection performance. In this paper, we propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection that allows for heavy down-sampling of unimportant background regions while preserving the fine-grained details of a high-resolution image. The resulting image is spatially smaller, leading to reduced computational costs while enabling a performance comparable to a high-resolution input. To achieve this, we propose a differentiable resampling module based on a thin plate spline spatial transformer network (TPS-STN). This module is regularized by a novel loss to provide an explicit supervision signal to learn to "magnify" salient regions. We report state-of-the-art results in the low compute regime on the ImageNet-VID and UA-DETRAC video object detection datasets. We demonstrate that on both datasets, the mAP of an EfficientDet-D1 (EfficientDet-D2) gets on par with EfficientDet-D2 (EfficientDet-D3) at a much lower computational cost. We also show that SALISA significantly improves the detection of small objects. In particular, SALISA with an EfficientDet-D1 detector improves the detection of small objects by $77\%$, and remarkably also outperforms EfficientDetD3 baseline.

Amirhossein Habibian, Haitam Ben Yahia, Davide Abati et al.

This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion alignment, such as optical flow, we propose a novel knowledge distillation schema coined as Delta Distillation. In our proposal, the student learns the variations in the teacher's intermediate features over time. We demonstrate that these temporal variations can be effectively distilled due to the temporal redundancies within video frames. During inference, both teacher and student cooperate for providing predictions: the former by providing initial representations extracted only on the key-frame, and the latter by iteratively estimating and applying deltas for the successive frames. Moreover, we consider various design choices to learn optimal student architectures including an end-to-end learnable architecture search. By extensive experiments on a wide range of architectures, including the most efficient ones, we demonstrate that delta distillation sets a new state of the art in terms of accuracy vs. efficiency trade-off for semantic segmentation and object detection in videos. Finally, we show that, as a by-product, delta distillation improves the temporal consistency of the teacher model.

Shubhankar Borse, Hyojin Park, Hong Cai et al.

This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation. In existing works, it is common to use a shared backbone to extract features for both things (countable classes such as vehicles) and stuff (uncountable classes such as roads). This, however, fails to capture the rich relations among them, which can be utilized to enhance visual understanding and segmentation performance. To address this shortcoming, we propose a novel Panoptic, Instance, and Semantic Relations (PISR) module to exploit such contexts. First, we generate panoptic encodings to summarize key features of the semantic classes and predicted instances. A Panoptic Relational Attention (PRA) module is then applied to the encodings and the global feature map from the backbone. It produces a feature map that captures 1) the relations across semantic classes and instances and 2) the relations between these panoptic categories and spatial features. PISR also automatically learns to focus on the more important instances, making it robust to the number of instances used in the relational attention module. Moreover, PISR is a general module that can be applied to any existing panoptic segmentation architecture. Through extensive evaluations on panoptic segmentation benchmarks like Cityscapes, COCO, and ADE20K, we show that PISR attains considerable improvements over existing approaches.

Shubhankar Borse, Debasmit Das, Hyojin Park et al.

We present DejaVu, a novel framework which leverages conditional image regeneration as additional supervision during training to improve deep networks for dense prediction tasks such as segmentation, depth estimation, and surface normal prediction. First, we apply redaction to the input image, which removes certain structural information by sparse sampling or selective frequency removal. Next, we use a conditional regenerator, which takes the redacted image and the dense predictions as inputs, and reconstructs the original image by filling in the missing structural information. In the redacted image, structural attributes like boundaries are broken while semantic context is largely preserved. In order to make the regeneration feasible, the conditional generator will then require the structure information from the other input source, i.e., the dense predictions. As such, by including this conditional regeneration objective during training, DejaVu encourages the base network to learn to embed accurate scene structure in its dense prediction. This leads to more accurate predictions with clearer boundaries and better spatial consistency. When it is feasible to leverage additional computation, DejaVu can be extended to incorporate an attention-based regeneration module within the dense prediction network, which further improves accuracy. Through extensive experiments on multiple dense prediction benchmarks such as Cityscapes, COCO, ADE20K, NYUD-v2, and KITTI, we demonstrate the efficacy of employing DejaVu during training, as it outperforms SOTA methods at no added computation cost.

Risheek Garrepalli, Jisoo Jeong, Rajeswaran C Ravindran et al.

Recent advancements in neural network-based optical flow estimation often come with prohibitively high computational and memory requirements, presenting challenges in their model adaptation for mobile and low-power use cases. In this paper, we introduce a lightweight low-latency and memory-efficient model, Dynamic Iterative Field Transforms (DIFT), for optical flow estimation feasible for edge applications such as mobile, XR, micro UAVs, robotics and cameras. DIFT follows an iterative refinement framework leveraging variable resolution of cost volumes for correspondence estimation. We propose a memory efficient solution for cost volume processing to reduce peak memory. Also, we present a novel dynamic coarse-to-fine cost volume processing during various stages of refinement to avoid multiple levels of cost volumes. We demonstrate first real-time cost-volume based optical flow DL architecture on Snapdragon 8 Gen 1 HTP efficient mobile AI accelerator with 32 inf/sec and 5.89 EPE (endpoint error) on KITTI with manageable accuracy-performance tradeoffs.

Pierre-David Letourneau, Manish Kumar Singh, Hsin-Pai Cheng et al.

We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Notably, several recent alternative attention mechanisms, including Hyena, Mamba, SimA, Conv2Former, and Castling-ViT, can be viewed as specific instances of our PADRe framework. PADRe leverages polynomial functions and draws upon established results from approximation theory, enhancing computational efficiency without compromising accuracy. PADRe's key components include multiplicative nonlinearities, which we implement using straightforward, hardware-friendly operations such as Hadamard products, incurring only linear computational and memory costs. PADRe further avoids the need for using complex functions such as Softmax, yet it maintains comparable or superior accuracy compared to traditional self-attention. We assess the effectiveness of PADRe as a drop-in replacement for self-attention across diverse computer vision tasks. These tasks include image classification, image-based 2D object detection, and 3D point cloud object detection. Empirical results demonstrate that PADRe runs significantly faster than the conventional self-attention (11x ~ 43x faster on server GPU and mobile NPU) while maintaining similar accuracy when substituting self-attention in the transformer models.

Debasmit Das, Shubhankar Borse, Hyojin Park et al.

Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-world, where samples arrive one-by-one in an online fashion. To tackle online settings, we propose TransAdapt, a framework that uses transformer and input transformations to improve segmentation performance. Specifically, we pre-train a transformer-based module on a segmentation network that transforms unsupervised segmentation output to a more reliable supervised output, without requiring test-time online training. To also facilitate test-time adaptation, we propose an unsupervised loss based on the transformed input that enforces the model to be invariant and equivariant to photometric and geometric perturbations, respectively. Overall, our framework produces higher quality segmentation masks with up to 17.6% and 2.8% mIOU improvement over no-adaptation and competitive baselines, respectively.

Kambiz Azarian, Debasmit Das, Hyojin Park et al.

We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we allow test-time modification of the segmentation network's weights using a single unlabeled test image. In this approach, we do not assume test-time access to the labeled source dataset. More specifically, our TTA method consists of using the keypoints estimates as pseudo labels and backpropagating them to adjust the backbone weights. The second approach is a training-time generalization (TTG) method, where we permit offline access to the labeled source dataset but not the test-time modification of weights. Furthermore, we do not assume the availability of any images from or knowledge about the target domain. Our TTG method consists of augmenting the backbone features with those generated by the keypoints head and feeding the aggregate vector to the mask head. Through a comprehensive set of ablations, we evaluate both approaches and identify several factors limiting the TTA gains. In particular, we show that in the absence of a significant domain shift, TTA may hurt and TTG show only a small gain in performance, whereas for a large domain shift, TTA gains are smaller and dependent on the heuristics used, while TTG gains are larger and robust to architectural choices.

Davide Belli, Debasmit Das, Bence Major et al.

Face authentication systems require a robust anti-spoofing module as they can be deceived by fabricating spoof images of authorized users. Most recent face anti-spoofing methods rely on optimized architectures and training objectives to alleviate the distribution shift between train and test users. However, in real online scenarios, past data from a user contains valuable information that could be used to alleviate the distribution shift. We thus introduce OAP (Online Adaptive Personalization): a lightweight solution which can adapt the model online using unlabeled data. OAP can be applied on top of most anti-spoofing methods without the need to store original biometric images. Through experimental evaluation on the SiW dataset, we show that OAP improves recognition performance of existing methods on both single video setting and continual setting, where spoof videos are interleaved with live ones to simulate spoofing attacks. We also conduct ablation studies to confirm the design choices for our solution.

Muzammal Naseer, Salman Khan, Fatih Porikli et al.

Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show significant robustness against popular and well studied adversarial attacks such as PGD. High adversarial robustness can also arise if an attack fails to find adversarial gradient directions, a phenomenon known as `gradient masking'. In this work, we analyse the effect of label smoothing on adversarial training as one of the potential causes of gradient masking. We then develop a guided mechanism to avoid local minima during attack optimization, leading to a novel attack dubbed Guided Projected Gradient Attack (G-PGA). Our attack approach is based on a `match and deceive' loss that finds optimal adversarial directions through guidance from a surrogate model. Our modified attack does not require random restarts, large number of attack iterations or search for an optimal step-size. Furthermore, our proposed G-PGA is generic, thus it can be combined with an ensemble attack strategy as we demonstrate for the case of Auto-Attack, leading to efficiency and convergence speed improvements. More than an effective attack, G-PGA can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses.

Animesh Karnewar, Denis Korzhenkov, Ioannis Lelekas et al.

We introduce Neodragon, a text-to-video system capable of generating 2s (49 frames @24 fps) videos at the 640x1024 resolution directly on a Qualcomm Hexagon NPU in a record 6.7s (7 FPS). Differing from existing transformer-based offline text-to-video generation models, Neodragon is the first to have been specifically optimised for mobile hardware to achieve efficient and high-fidelity video synthesis. We achieve this through four key technical contributions: (1) Replacing the original large 4.762B T5xxl Text-Encoder with a much smaller 0.2B DT5 (DistilT5) with minimal quality loss, enabled through a novel Text-Encoder Distillation procedure. (2) Proposing an Asymmetric Decoder Distillation approach allowing us to replace the native codec-latent-VAE decoder with a more efficient one, without disturbing the generative latent-space of the generation pipeline. (3) Pruning of MMDiT blocks within the denoiser backbone based on their relative importance, with recovery of original performance through a two-stage distillation process. (4) Reducing the NFE (Neural Functional Evaluation) requirement of the denoiser by performing step distillation using DMD adapted for pyramidal flow-matching, thereby substantially accelerating video generation. When paired with an optimised SSD1B first-frame image generator and QuickSRNet for 2x super-resolution, our end-to-end Neodragon system becomes a highly parameter (4.945B full model), memory (3.5GB peak RAM usage), and runtime (6.7s E2E latency) efficient mobile-friendly model, while achieving a VBench total score of 81.61. By enabling low-cost, private, and on-device text-to-video synthesis, Neodragon democratizes AI-based video content creation, empowering creators to generate high-quality videos without reliance on cloud services. Code and model will be made publicly available at our website: https://qualcomm-ai-research.github.io/neodragon

Rajeev Yasarla, Deepti Hegde, Shizhong Han et al.

Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation learning from sparse trajectory annotations and under-utilize their potential as generative models. We propose Generative Scenario Rollouts (GeRo), a plug-and-play framework for VLA models that jointly performs planning and generation of language-grounded future traffic scenes through an autoregressive rollout strategy. First, a VLA model is trained to encode ego vehicle and agent dynamics into latent tokens under supervision from planning, motion, and language tasks, facilitating text-aligned generation. Next, GeRo performs language-conditioned autoregressive generation. Given multi-view images, a scenario description, and ego-action questions, it generates future latent tokens and textual responses to guide long-horizon rollouts. A rollout-consistency loss stabilizes predictions using ground truth or pseudo-labels, mitigating drift and preserving text-action alignment. This design enables GeRo to perform temporally consistent, language-grounded rollouts that support long-horizon reasoning and multi-agent planning. On Bench2Drive, GeRo improves driving score and success rate by +15.7 and +26.2, respectively. By integrating reinforcement learning with generative rollouts, GeRo achieves state-of-the-art closed-loop and open-loop performance, demonstrating strong zero-shot robustness. These results highlight the promise of generative, language-conditioned reasoning as a foundation for safer and more interpretable end-to-end autonomous driving.

Hyojin Park, Yi Li, Janghoon Cho et al.

Despite decades of work, surveillance still struggles to find specific targets across long, multi-camera video. Prior methods -- tracking pipelines, CLIP based models, and VideoRAG -- require heavy manual filtering, capture only shallow attributes, and fail at temporal reasoning. Real-world searches are inherently multimodal (e.g., "When does this person join the fight?" with the person's image), yet this setting remains underexplored. Also, there are no proper benchmarks to evaluate those setting - asking video with multimodal queries. To address this gap, we introduce ForeSeaQA, a new benchmark specifically designed for video QA with image-and-text queries and timestamped annotations of key events. The dataset consists of long-horizon surveillance footage paired with diverse multimodal questions, enabling systematic evaluation of retrieval, temporal grounding, and multimodal reasoning in realistic forensic conditions. Not limited to this benchmark, we propose ForeSea, an AI forensic search system with a 3-stage, plug-and-play pipeline. (1) A tracking module filters irrelevant footage; (2) a multimodal embedding module indexes the remaining clips; and (3) during inference, the system retrieves top-K candidate clips for a Video Large Language Model (VideoLLM) to answer queries and localize events. On ForeSeaQA, ForeSea improves accuracy by 3.5% and temporal IoU by 11.0 over prior VideoRAG models. To our knowledge, ForeSeaQA is the first benchmark to support complex multimodal queries with precise temporal grounding, and ForeSea is the first VideoRAG system built to excel in this setting.

Sunghyun Park, Jeongho Kim, Hyoungwoo Park et al.

Diffusion Transformers (DiTs) have significantly enhanced text-to-image (T2I) generation quality, enabling high-quality personalized content creation. However, fine-tuning these models requires substantial computational complexity and memory, limiting practical deployment under resource constraints. To tackle these challenges, we propose a memory-efficient fine-tuning framework called DiT-BlockSkip, integrating timestep-aware dynamic patch sampling and block skipping by precomputing residual features. Our dynamic patch sampling strategy adjusts patch sizes based on the diffusion timestep, then resizes the cropped patches to a fixed lower resolution. This approach reduces forward & backward memory usage while allowing the model to capture global structures at higher timesteps and fine-grained details at lower timesteps. The block skipping mechanism selectively fine-tunes essential transformer blocks and precomputes residual features for the skipped blocks, significantly reducing training memory. To identify vital blocks for personalization, we introduce a block selection strategy based on cross-attention masking. Evaluations demonstrate that our approach achieves competitive personalization performance qualitatively and quantitatively, while reducing memory usage substantially, moving toward on-device feasibility (e.g., smartphones, IoT devices) for large-scale diffusion transformers.

Shweta Mahajan, Shreya Kadambi, Hoang Le et al.

We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating physically plausible scene transformations driven by real-world actions. Unlike prior work focused on object-level edits, Do-Undo requires models to simulate the outcome of a physical action and then accurately reverse it, reflecting true cause-and-effect in the visual world. We curate a large-scale dataset of reversible actions from real-world videos and design a training strategy enforcing consistency for robust action grounding. Our experiments reveal that current models struggle with physical reversibility, underscoring the importance of this task for embodied AI, robotics, and physics-aware generative modeling. Do-Undo establishes an intuitive testbed for evaluating and advancing physical reasoning in multimodal systems.

Wentao Ni, Kangqi Zhang, Zhongming Yu et al.

As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse attention cannot adapt to heterogeneous attention distributions across heads and layers, whereas top-p sparse attention directly preserves attention mass and provides stronger accuracy guarantees. Existing top-p methods, however, fail to jointly optimize top-p accuracy, selection overhead, and sparse attention cost, which limits their overall efficiency. We present Double-P, a hierarchical sparse attention framework that optimizes all three stages. Double-P first performs coarse-grained top-p estimation at the cluster level using size-weighted centroids, then adaptively refines computation through a second top-p stage that allocates token-level attention only when needed. Across long-context benchmarks, Double-P consistently achieves near-zero accuracy drop, reducing attention computation overhead by up to 1.8x and delivers up to 1.3x end-to-end decoding speedup over state-of-the-art fixed-budget sparse attention methods.

Zhuojin Li, Hsin-Pai Cheng, Hong Cai et al.

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across vision tasks. CoReDiT uses a linear-time spatial coherence score to estimate local redundancy in the latent token lattice and skips high coherence (redundant) tokens in self-attention. To maintain a dense representation and avoid visual discontinuities, we reconstruct skipped attention outputs via coherence-guided aggregation of spatially neighboring retained tokens. We further introduce a progressive, block-adaptive pruning schedule that increases pruning gradually and allocates larger budgets to blocks and denoising steps with higher redundancy. Across state-of-the-art diffusion backbones including PixArt-α and MagicDrive-V2, CoReDiT achieves up to 55% self-attention FLOPs reduction and inference speedups of 1.33x on cloud GPUs and 1.72x on mobile NPUs, while maintaining high visual quality. Notably, CoReDiT also increases on-device memory head-room, enabling higher-resolution generation.

Janghoon Cho, Jungsoo Lee, Munawar Hayat et al.

Recent studies in long video understanding have harnessed the advanced visual-language reasoning capabilities of Large Multimodal Models (LMMs), driving the evolution of video-LMMs specialized for processing extended video sequences. However, the scalability of these models is severely limited by the overwhelming volume of visual tokens generated from extended video sequences. To address this challenge, this paper proposes FLoC, an efficient visual token compression framework based on the facility location function, a principled approach that swiftly selects a compact yet highly representative and diverse subset of visual tokens within a predefined budget on the number of visual tokens. By integrating the lazy greedy algorithm, our method achieves remarkable efficiency gains by swiftly selecting a compact subset of tokens, drastically reducing the number of visual tokens while guaranteeing near-optimal performance. Notably, our approach is training-free, model-agnostic, and query-agnostic, providing a versatile solution that seamlessly integrates with diverse video-LLMs and existing workflows. Extensive evaluations on large-scale benchmarks, such as Video-MME, MLVU, and LongVideoBench, demonstrate that our framework consistently surpasses recent compression techniques, highlighting not only its effectiveness and robustness in addressing the critical challenges of long video understanding, but also its efficiency in processing speed.

Rajeev Yasarla, Deepti Hegde, Hsin-Pai Cheng et al.

Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional imitation learning framework. Existing closed-loop supervision approaches lack scalability and fail to completely model a reactive environment. We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model. The ego vehicle and nearby traffic agents are independently controlled over multi-step horizons, while being reactive to other agents in the scene, enabling closed-loop training. MAPLE consists of two training stages: (1) supervised fine-tuning on the latent rollouts based on ground-truth trajectories, followed by (2) reinforcement learning with global and agent -specific rewards that encourage safety, progress, and interaction realism. We further propose diversity rewards that encourage the model to generate planning behaviors that may not be present in logged driving data. Notably, our closed-loop training framework is scalable and does not require external simulators, which can be computationally expensive to run and have limited visual fidelity to the real-world. MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.

Shubhankar Borse, Farzad Farhadzadeh, Munawar Hayat et al.

State-of-the-art text-to-image models excel at realism but collapse on multi-human prompts - duplicating faces, merging identities, and miscounting individuals. We introduce DisCo (Reinforcement with Diversity Constraints), the first RL-based framework to directly optimize identity diversity in multi-human generation. DisCo fine-tunes flow-matching models via Group-Relative Policy Optimization (GRPO) with a compositional reward that (i) penalizes intra-image facial similarity, (ii) discourages cross-sample identity repetition, (iii) enforces accurate person counts, and (iv) preserves visual fidelity through human preference scores. A single-stage curriculum stabilizes training as complexity scales, requiring no extra annotations. On the DiverseHumans Testset, DisCo achieves 98.6 Unique Face Accuracy and near-perfect Global Identity Spread - surpassing both open-source and proprietary methods (e.g., Gemini, GPT-Image) while maintaining competitive perceptual quality. Our results establish DisCo as a scalable, annotation-free solution that resolves the long-standing identity crisis in generative models and sets a new benchmark for compositional multi-human generation.

Sudhanshu Agrawal, Risheek Garrepalli, Raghavv Goel et al.

Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token generation rates. However, currently available open-source dLLMs often generate at much lower rates, typically decoding only a single token at every denoising timestep in order to maximize output quality. We present Spiffy, a speculative decoding algorithm that accelerates dLLM inference by $\mathbf{2.8{-}3.1\times}$ while provably preserving the model's output distribution. This work addresses the unique challenges involved in applying ideas from speculative decoding of AR-LLMs to the dLLM setting. Spiffy proposes draft states by leveraging the dLLM's distribution itself in an auto-speculative manner. This approach is efficient and effective, and eliminates the overheads of training and running an independent draft model. To structure the candidate draft states, we propose a novel directed draft graph which is uniquely designed to take advantage of the bidirectional, block-wise nature of dLLM generation and can be verified in parallel by the dLLM. To further optimize the structure of these draft graphs, we introduce an efficient, offline calibration algorithm that procedurally determines high-quality graph configurations. These optimized draft graphs, enabling increased acceptance rates, lead to a significant boost in the overall speedup achieved by the system. Crucially, Spiffy is also complementary to other recent innovations in improving dLLM generation speeds such as KV-caching and multi-token unmasking. We demonstrate that when combined with such parallel decoding algorithms, Spiffy is able to effectively multiply the benefits of these methods leading to total speedups of up to $\mathbf{7.9\times}$.

Shubhankar Borse, Seokeon Choi, Sunghyun Park et al.

Generation of images containing multiple humans, performing complex actions, while preserving their facial identities, is a significant challenge. A major factor contributing to this is the lack of a dedicated benchmark. To address this, we introduce MultiHuman-Testbench, a novel benchmark for rigorously evaluating generative models for multi-human generation. The benchmark comprises 1,800 samples, including carefully curated text prompts, describing a range of simple to complex human actions. These prompts are matched with a total of 5,550 unique human face images, sampled uniformly to ensure diversity across age, ethnic background, and gender. Alongside captions, we provide human-selected pose conditioning images which accurately match the prompt. We propose a multi-faceted evaluation suite employing four key metrics to quantify face count, ID similarity, prompt alignment, and action detection. We conduct a thorough evaluation of a diverse set of models, including zero-shot approaches and training-based methods, with and without regional priors. We also propose novel techniques to incorporate image and region isolation using human segmentation and Hungarian matching, significantly improving ID similarity. Our proposed benchmark and key findings provide valuable insights and a standardized tool for advancing research in multi-human image generation. The dataset and evaluation codes will be available at https://github.com/Qualcomm-AI-research/MultiHuman-Testbench.

Tianfei Zhou, Fatih Porikli, David Crandall et al.

Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to creating virtual background in video conferencing. Recently, with the renaissance of connectionism in computer vision, there has been an influx of deep learning based approaches for video segmentation that have delivered compelling performance. In this survey, we comprehensively review two basic lines of research -- generic object segmentation (of unknown categories) in videos, and video semantic segmentation -- by introducing their respective task settings, background concepts, perceived need, development history, and main challenges. We also offer a detailed overview of representative literature on both methods and datasets. We further benchmark the reviewed methods on several well-known datasets. Finally, we point out open issues in this field, and suggest opportunities for further research. We also provide a public website to continuously track developments in this fast advancing field: https://github.com/tfzhou/VS-Survey.

Muzammal Naseer, Salman Khan, Munawar Hayat et al.

While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific `targeted' class remains a challenging feat. In this paper, we propose a new generative approach for highly transferable targeted perturbations (\ours). We note that the existing methods are less suitable for this task due to their reliance on class-boundary information that changes from one model to another, thus reducing transferability. In contrast, our approach matches the perturbed image `distribution' with that of the target class, leading to high targeted transferability rates. To this end, we propose a new objective function that not only aligns the global distributions of source and target images, but also matches the local neighbourhood structure between the two domains. Based on the proposed objective, we train a generator function that can adaptively synthesize perturbations specific to a given input. Our generative approach is independent of the source or target domain labels, while consistently performs well against state-of-the-art methods on a wide range of attack settings. As an example, we achieve $32.63\%$ target transferability from (an adversarially weak) VGG19$_{BN}$ to (a strong) WideResNet on ImageNet val. set, which is 4$\times$ higher than the previous best generative attack and 16$\times$ better than instance-specific iterative attack. Code is available at: {\small\url{https://github.com/Muzammal-Naseer/TTP}}.

Muzammal Naseer, Salman Khan, Munawar Hayat et al.

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock towards their real-world deployment. Transferability of adversarial examples demand generalizable defenses that can provide cross-task protection. Adversarial training that enhances robustness by modifying target model's parameters lacks such generalizability. On the other hand, different input processing based defenses fall short in the face of continuously evolving attacks. In this paper, we take the first step to combine the benefits of both approaches and propose a self-supervised adversarial training mechanism in the input space. By design, our defense is a generalizable approach and provides significant robustness against the \textbf{unseen} adversarial attacks (\eg by reducing the success rate of translation-invariant \textbf{ensemble} attack from 82.6\% to 31.9\% in comparison to previous state-of-the-art). It can be deployed as a plug-and-play solution to protect a variety of vision systems, as we demonstrate for the case of classification, segmentation and detection. Code is available at: {\small\url{https://github.com/Muzammal-Naseer/NRP}}.

Hafeez Anwar, Saeed Anwar, Sebastian Zambanini et al.

We perform the classification of ancient Roman Republican coins via recognizing their reverse motifs where various objects, faces, scenes, animals, and buildings are minted along with legends. Most of these coins are eroded due to their age and varying degrees of preservation, thereby affecting their informative attributes for visual recognition. Changes in the positions of principal symbols on the reverse motifs also cause huge variations among the coin types. Lastly, in-plane orientations, uneven illumination, and a moderate background clutter further make the classification task non-trivial and challenging. To this end, we present a novel network model, CoinNet, that employs compact bilinear pooling, residual groups, and feature attention layers. Furthermore, we gathered the largest and most diverse image dataset of the Roman Republican coins that contains more than 18,000 images belonging to 228 different reverse motifs. On this dataset, our model achieves a classification accuracy of more than \textbf{98\%} and outperforms the conventional bag-of-visual-words based approaches and more recent state-of-the-art deep learning methods. We also provide a detailed ablation study of our network and its generalization capability. Models and Datasets available at https://github.com/saeed-anwar/CoinNet

Guodong Ding, Salman Khan, Zhenmin Tang et al.

Person re-identification aims to establish the correct identity correspondences of a person moving through a non-overlapping multi-camera installation. Recent advances based on deep learning models for this task mainly focus on supervised learning scenarios where accurate annotations are assumed to be available for each setup. Annotating large scale datasets for person re-identification is demanding and burdensome, which renders the deployment of such supervised approaches to real-world applications infeasible. Therefore, it is necessary to train models without explicit supervision in an autonomous manner. In this paper, we propose an elegant and practical clustering approach for unsupervised person re-identification based on the cluster validity consideration. Concretely, we explore a fundamental concept in statistics, namely \emph{dispersion}, to achieve a robust clustering criterion. Dispersion reflects the compactness of a cluster when employed at the intra-cluster level and reveals the separation when measured at the inter-cluster level. With this insight, we design a novel Dispersion-based Clustering (DBC) approach which can discover the underlying patterns in data. This approach considers a wider context of sample-level pairwise relationships to achieve a robust cluster affinity assessment which handles the complications may arise due to prevalent imbalanced data distributions. Additionally, our solution can automatically prioritize standalone data points and prevents inferior clustering. Our extensive experimental analysis on image and video re-identification benchmarks demonstrate that our method outperforms the state-of-the-art unsupervised methods by a significant margin. Code is available at https://github.com/gddingcs/Dispersion-based-Clustering.git.

Antoine Mercier, Ramin Nakhli, Mahesh Reddy et al.

Despite the latest remarkable advances in generative modeling, efficient generation of high-quality 3D assets from textual prompts remains a difficult task. A key challenge lies in data scarcity: the most extensive 3D datasets encompass merely millions of assets, while their 2D counterparts contain billions of text-image pairs. To address this, we propose a novel approach which harnesses the power of large, pretrained 2D diffusion models. More specifically, our approach, HexaGen3D, fine-tunes a pretrained text-to-image model to jointly predict 6 orthographic projections and the corresponding latent triplane. We then decode these latents to generate a textured mesh. HexaGen3D does not require per-sample optimization, and can infer high-quality and diverse objects from textual prompts in 7 seconds, offering significantly better quality-to-latency trade-offs when comparing to existing approaches. Furthermore, HexaGen3D demonstrates strong generalization to new objects or compositions.

Kumara Kahatapitiya, Adil Karjauv, Davide Abati et al.

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy memory and computational costs to generate temporally-coherent frames, either in the form of diffusion inversion and/or cross-frame attention. In this paper, we conduct an analysis of such inefficiencies, and suggest simple yet effective modifications that allow significant speed-ups whilst maintaining quality. Moreover, we introduce Object-Centric Diffusion, to fix generation artifacts and further reduce latency by allocating more computations towards foreground edited regions, arguably more important for perceptual quality. We achieve this by two novel proposals: i) Object-Centric Sampling, decoupling the diffusion steps spent on salient or background regions and spending most on the former, and ii) Object-Centric Token Merging, which reduces cost of cross-frame attention by fusing redundant tokens in unimportant background regions. Both techniques are readily applicable to a given video editing model without retraining, and can drastically reduce its memory and computational cost. We evaluate our proposals on inversion-based and control-signal-based editing pipelines, and show a latency reduction up to 10x for a comparable synthesis quality. Project page: qualcomm-ai-research.github.io/object-centric-diffusion.

Deepti Hegde, Rajeev Yasarla, Hong Cai et al.

Autonomous driving demands safe motion planning, especially in critical "long-tail" scenarios. Recent end-to-end autonomous driving systems leverage large language models (LLMs) as planners to improve generalizability to rare events. However, using LLMs at test time introduces high computational costs. To address this, we propose DiMA, an end-to-end autonomous driving system that maintains the efficiency of an LLM-free (or vision-based) planner while leveraging the world knowledge of an LLM. DiMA distills the information from a multi-modal LLM to a vision-based end-to-end planner through a set of specially designed surrogate tasks. Under a joint training strategy, a scene encoder common to both networks produces structured representations that are semantically grounded as well as aligned to the final planning objective. Notably, the LLM is optional at inference, enabling robust planning without compromising on efficiency. Training with DiMA results in a 37% reduction in the L2 trajectory error and an 80% reduction in the collision rate of the vision-based planner, as well as a 44% trajectory error reduction in longtail scenarios. DiMA also achieves state-of-the-art performance on the nuScenes planning benchmark.

Qiqi Hou, Randall Rauwendaal, Zifeng Li et al.

Recently, 3D Gaussian Splatting (3DGS) has emerged as a significant advancement in 3D scene reconstruction, attracting considerable attention due to its ability to recover high-fidelity details while maintaining low complexity. Despite the promising results achieved by 3DGS, its rendering performance is constrained by its dependence on costly non-commutative alpha-blending operations. These operations mandate complex view dependent sorting operations that introduce computational overhead, especially on the resource-constrained platforms such as mobile phones. In this paper, we propose Weighted Sum Rendering, which approximates alpha blending with weighted sums, thereby removing the need for sorting. This simplifies implementation, delivers superior performance, and eliminates the "popping" artifacts caused by sorting. Experimental results show that optimizing a generalized Gaussian splatting formulation to the new differentiable rendering yields competitive image quality. The method was implemented and tested in a mobile device GPU, achieving on average $1.23\times$ faster rendering.