We present ProtoDepth, a novel prototype-based approach for continual learning of unsupervised depth completion, the multimodal 3D reconstruction task of predicting dense depth maps from RGB images and sparse point clouds. The unsupervised learning paradigm is well-suited for continual learning, as ground truth is not needed. However, when training on new non-stationary distributions, depth completion models will catastrophically forget previously learned information. We address forgetting by learning prototype sets that adapt the latent features of a frozen pretrained model to new domains. Since the original weights are not modified, ProtoDepth does not forget when test-time domain identity is known. To extend ProtoDepth to the challenging setting where the test-time domain identity is withheld, we propose to learn domain descriptors that enable the model to select the appropriate prototype set for inference. We evaluate ProtoDepth on benchmark dataset sequences, where we reduce forgetting compared to baselines by 52.2% for indoor and 53.2% for outdoor to achieve the state of the art. Project Page: https://protodepth.github.io/.

We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some ``source'' data, often predict erroneous outputs when transferred to ``target'' data captured in novel environmental conditions due to a covariate shift. The crux of our method lies in quantifying the likelihood of depth predictions belonging to the source data distribution. The challenge is in the lack of access to out-of-distribution (target) data prior to deployment. Hence, rather than making assumptions regarding the target distribution, we utilize adversarial perturbations as a mechanism to explore the data space. This enables us to train an energy model that scores local regions of depth predictions as in- or out-of-distribution. We update the parameters of pretrained depth completion models at test time to minimize energy, effectively aligning test-time predictions to those of the source distribution. We call our method ``Energy-based Test-time Adaptation'', or ETA for short. We evaluate our method across three indoor and three outdoor datasets, where ETA improve over the previous state-of-the-art method by an average of 6.94% for outdoors and 10.23% for indoors. Project Page: https://fuzzythecat.github.io/eta.

We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being trained on tens of millions of images, FMDEs are susceptible to the covariate shift introduced by changes in camera calibration (intrinsic, distortion) parameters, leading to erroneous depth estimates. Our method aligns the distribution of latent embeddings encoding fisheye images to those of perspective images, enabling the reuse of FMDEs for fisheye cameras without retraining or finetuning. To this end, we introduce a set of Calibration Tokens as a light-weight adaptation mechanism that modulates the latent embeddings for alignment. By exploiting the already expressive latent space of FMDEs, we posit that modulating their embeddings avoids the negative impact of artifacts and loss introduced in conventional recalibration or map projection to a canonical reference frame in the image space. Our method is self-supervised and does not require fisheye images but leverages publicly available large-scale perspective image datasets. This is done by recalibrating perspective images to fisheye images, and enforcing consistency between their estimates during training. We evaluate our approach with several FMDEs, on both indoors and outdoors, where we consistently improve over state-of-the-art methods using a single set of tokens for both. Code available at: https://github.com/JungHeeKim29/calibration-token; https://github.com/Suchisrit/CalibrationTokens.

We propose a model-agnostic, progressive test-time energy adaptation approach for medical image segmentation. Maintaining model performance across diverse medical datasets is challenging, as distribution shifts arise from inconsistent imaging protocols and patient variations. Unlike domain adaptation methods that require multiple passes through target data - impractical in clinical settings - our approach adapts pretrained models progressively as they process test data. Our method leverages a shape energy model trained on source data, which assigns an energy score at the patch level to segmentation maps: low energy represents in-distribution (accurate) shapes, while high energy signals out-of-distribution (erroneous) predictions. By minimizing this energy score at test time, we refine the segmentation model to align with the target distribution. To validate the effectiveness and adaptability, we evaluated our framework on eight public MRI (bSSFP, T1- and T2-weighted) and X-ray datasets spanning cardiac, spinal cord, and lung segmentation. We consistently outperform baselines both quantitatively and qualitatively.

Labeling LiDAR point clouds is notoriously time-and-energy-consuming, which spurs recent unsupervised 3D representation learning methods to alleviate the labeling burden in LiDAR perception via pretrained weights. Existing work focus on either masked auto encoding or contrastive learning on LiDAR point clouds, which neglects the temporal LiDAR sequence that naturally accounts for object motion (and their semantics). Instead, we propose TREND, short for Temporal REndering with Neural fielD, to learn 3D representation via forecasting the future observation in an unsupervised manner. TREND integrates forecasting for 3D pre-training through a Recurrent Embedding scheme to generate 3D embeddings across time and a Temporal LiDAR Neural Field specifically designed for LiDAR modality to represent the 3D scene, with which we compute the loss using differentiable rendering. We evaluate TREND on 3D object detection and LiDAR semantic segmentation tasks on popular datasets, including Once, Waymo, NuScenes, and SemanticKITTI. TREND generally improves from-scratch models across datasets and tasks and brings gains of 1.77\% mAP on Once and 2.11\% mAP on NuScenes, which are up to 400\% more improvement compared to previous SOTA unsupervised 3D pre-training methods. Codes and models will be available.

Speculative decoding is a technique to leverage hardware concurrency in order to enable multiple steps of token generation in a single forward pass, thus improving the efficiency of large-scale autoregressive (AR) Transformer models. State-space models (SSMs) are already more efficient than AR Transformers, since their state summarizes all past data with no need to cache or re-process tokens in the sliding window context. However, their state can also comprise thousands of tokens; so, speculative decoding has recently been extended to SSMs. Existing approaches, however, do not leverage the tree-based verification methods, since current SSMs lack the means to compute a token tree efficiently. We propose the first scalable algorithm to perform tree-based speculative decoding in state-space models (SSMs) and hybrid architectures of SSMs and Transformer layers. We exploit the structure of accumulated state transition matrices to facilitate tree-based speculative decoding with minimal overhead relative to current SSM implementations. Along with the algorithm, we describe a hardware-aware implementation that improves naive application of AR Transformer tree-based speculative decoding methods to SSMs. Furthermore, we outperform vanilla speculative decoding with SSMs even with a baseline drafting model and tree structure on three different benchmarks, opening up opportunities for further speed up with SSM and hybrid model inference. Code can be find at: https://github.com/wyc1997/stree.

We describe a method for recovering the irradiance underlying a collection of images corrupted by atmospheric turbulence. Since supervised data is often technically im-possible to obtain, assumptions and biases have to be im-posed to solve this inverse problem, and we choose to model them explicitly. Rather than initializing a latent irradiance (“template”) by heuristics to estimate deformation, we se-lect one of the images as a reference, and model the de-formation in this image by the aggregation of the optical flow from it to other images, exploiting a prior imposed by Central Limit Theorem. Then with a novel flow inversion module, the model registers each image TO the template but WITHOUT the template, avoiding artifacts related to poor template initialization. To illustrate the robustness of the method, we simply (i) select the first frame as the ref-erence and (ii) use the simplest optical flow to estimate the warpings, yet the improvement in registration is decisive in the final reconstruction, as we achieve state-of-the-art per-formance despite its simplicity. The method establishes a strong baseline that can be further improved by integrating it seamlessly into more sophisticated pipelines, or with domain-specific methods if so desired.

It is common to observe performance degradation when transferring models trained on some (source) datasets to tar-get testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain adaptation (DA), may require the source data on which the model was trained (often not available), while others, i.e., source-free DA, require many passes through the testing data. We pro-pose an online test-time adaptation method for depth com-pletion, the task of inferring a dense depth map from a single image and associated sparse depth map, that closes the per-formance gap in a single pass. We first present a study on how the domain shift in each data modality affects model per-formance. Based on our observations that the sparse depth modality exhibits a much smaller covariate shift than the image, we design an embedding module trained in the source domain that preserves a mapping from features encoding only sparse depth to those encoding image and sparse depth. During test time, sparse depth features are projected using this map as a proxy for source domain features and are used as guidance to train a set of auxiliary parameters (i.e., adap-tation layer) to align image and sparse depth features from the target test domain to that of the source domain. We eval-uate our method on indoor and outdoor scenarios and show that it improves over baselines by an average of 21.1%. Code available at github.com/seobbroITTA-depth-completion.

Touch provides crucial information about the physical properties of the objects around us. Creating models that capture cross-modal associations between touch and other modalities, however, remains a challenging problem, due to wide variety of touch sensors and the intensive effort required to collect tactile data. We propose UniTouch, a unified model for vision-based touch sensors that connects their tactile signals to other modalities, including vision, language, and sound. We achieve this by aligning our tactile embeddings to pretrained image embeddings already associated with a variety of other modalities. We further propose learnable sensor-specific tokens, allowing the model to learn from a set of heterogeneous tactile sensors, all at the same time. UniTouch is capable of conducting various touch sensing tasks in a zero-shot setting, from robot grasping prediction to touch-based question answering. To the best of our knowledge, UniTouch is the first model to demonstrate these capabilities. Project Page: https://cfeng16.github.io/UniTouch/.

Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i. e. scale. Predicting a 3D scene from text descriptionis) is similarly ill-posed, i. e. spatial arrangements of objects described. We investigate the question of whether two inher-ently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we fo-cus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene. To this end, we begin by encoding the text caption as a mean and standard deviation; using a variational framework, we learn the distribution of the plausible metric reconstructions of 3D scenes corresponding to the text captions as a prior. To “select” a specific reconstruction or depth map, we encode the given image through a conditional sampler that samples from the latent space of the variational text encoder, which is then decoded to the output depth map. Our approach is trained alternatingly between the text and image branches: in one optimization step, we predict the mean and standard deviation from the text description and sample from a standard Gaussian, and in the other, we sample using a (image) conditional sampler. Once trained, we directly predict depth from the encoded text using the conditional sampler. We demonstrate our approach on indoor (NYUv2) and out-door (KITTI) scenarios, where we show that language can consistently improve performance in both. Code: https://github.com/Adonis-galaxy/WorDepth.

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding dimensionality, and results in semantically rich but spatially coarsely quantized feature maps. In order to retrieve spatial details beneficial to fine-grained inference tasks we propose a training-free method inspired by "stochastic resonance." Specifically, we perform sub-token spatial transformations to the input data, and aggregate the resulting ViT features after applying the inverse transformation. The resulting "Stochastic Resonance Transformer" (SRT) retains the rich semantic information of the original representation, but grounds it on a finer-scale spatial domain, partly mitigating the coarse effect of spatial tokenization. SRT is applicable across any layer of any ViT architecture, consistently boosting performance on several tasks including segmentation, classification, depth estimation, and others by up to 14.9% without the need for any fine-tuning. Code: https://github.com/donglao/srt.

We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty – we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities – depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 24% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 12.39% in all-day scenarios, 12.02% when tested specifically for daytime, and 14.95% for nighttime scenes. Code available at : https://github.com/ezhovv/all-day-depth

We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection during the image formation process. Any scale chosen is a bias, typically stemming from training on a dataset; hence, existing works have instead opted to use relative (normalized, inverse) depth. Our goal is to recover metric-scaled depth maps through a linear transformation. The crux of our method lies in the observation that certain objects (e.g., cars, trees, street signs) are typically found or associated with certain types of scenes (e.g., outdoor). We explore whether language descriptions can be used to transform relative depth predictions to those in metric scale. Our method, RSA , takes as input a text caption describing objects present in an image and outputs the parameters of a linear transformation which can be applied globally to a relative depth map to yield metric-scaled depth predictions. We demonstrate our method on recent general-purpose monocular depth models on indoors (NYUv2, VOID) and outdoors (KITTI). When trained on multiple datasets, RSA can serve as a general alignment module in zero-shot settings. Our method improves over common practices in aligning relative to metric depth and results in predictions that are comparable to an upper bound of fitting relative depth to ground truth via a linear transformation. Code is available at: https://github.com/Adonis-galaxy/RSA.

We present a method for inferring dense depth from a camera image and a sparse noisy radar point cloud. We first describe the mechanics behind mmWave radar point cloud formation and the challenges that it poses, i.e. ambiguous elevation and noisy depth and azimuth components that yields incorrect positions when projected onto the image, and how existing works have overlooked these nuances in camera-radar fusion. Our approach is motivated by these mechanics, leading to the design of a network that maps each radar point to the possible surfaces that it may project onto in the image plane. Unlike existing works, we do not process the raw radar point cloud as an erroneous depth map, but query each raw point independently to associate it with likely pixels in the image – yielding a semi-dense radar depth map. To fuse radar depth with an image, we propose a gated fusion scheme that accounts for the confidence scores of the correspondence so that we selectively combine radar and camera embeddings to yield a dense depth map. We test our method on the NuScenes benchmark and show a 10.3% improvement in mean absolute error and a 9.1% improvement in root-mean-square error over the best method. Code: https://github.com/nesl/radar-camera-fusion-depth.

Today single image deweathering is arguably more sensitive to the dataset type, rather than the model. We introduce WeatherStream, an automatic pipeline capturing all real-world weather effects (rain, snow, and rain fog degradations), along with their clean image pairs. Previous state-of-the-art methods that have attempted the all-weather removal task train on synthetic pairs, and are thus limited by the Sim2Real domain gap. Recent work has attempted to manually collect time multiplexed pairs, but the use of human labor limits the scale of such a dataset. We introduce a pipeline that uses the power of light-transport physics and a model trained on a small, initial seed dataset to reject approximately 99.6% of unwanted scenes. The pipeline is able to generalize to new scenes and degradations that can, in turn, be used to train existing models just like fully human-labeled data. Training on a dataset collected through this procedure leads to significant improvements on multiple existing weather removal methods on a carefully human-collected test set of real-world weather effects. The dataset and code can be found in the following website: http://visual.ee.ucla.edu/wstream.htm/.

While perspective is a well-studied topic in art, it is generally taken for granted in images. However, for the recent wave of high-quality image synthesis methods such as latent diffusion models, perspective accuracy is not an explicit requirement. Since these methods are capable of outputting a wide gamut of possible images, it is difficult for these synthesized images to adhere to the principles of linear perspective. We introduce a novel geometric constraint in the training process of generative models to enforce perspective accuracy. We show that outputs of models trained with this constraint both appear more realistic and improve performance of downstream models trained on generated images. Subjective human trials show that images generated with latent diffusion models trained with our constraint are preferred over images from the Stable Diffusion V2 model 70% of the time. SOTA monocular depth estimation models such as DPT and PixelFormer, fine-tuned on our images, outperform the original models trained on real images by up to 7.03% in RMSE and 19.3% in SqRel on the KITTI test set for zero-shot transfer.

We study the effect of adversarial perturbations of images on deep stereo matching networks for the disparity estimation task. We present a method to craft a single set of perturbations that, when added to any stereo image pair in a dataset, can fool a stereo network to significantly alter the perceived scene geometry. Our perturbation images are “universal” in that they not only corrupt estimates of the network on the dataset they are optimized for, but also generalize to different architectures trained on different datasets. We evaluate our approach on multiple benchmark datasets where our perturbations can increase the D1-error (akin to fooling rate) of state-of-the-art stereo networks from 1% to as much as 87%. We investigate the effect of perturbations on the estimated scene geometry and identify object classes that are most vulnerable. Our analysis on the activations of registered points between left and right images led us to find architectural components that can increase robustness against adversaries. By simply designing networks with such components, one can reduce the effect of adversaries by up to 60.5%, which rivals the robustness of networks finetuned with costly adversarial data augmentation. Our design principle also improves their robustness against common image corruptions by an average of 70%.

We study the effect of adversarial perturbations of images on the estimates of disparity by deep learning models trained for stereo. We show that imperceptible additive perturbations can significantly alter the disparity map, and correspondingly the perceived geometry of the scene. These perturbations not only affect the specific model they are crafted for, but transfer to models with different architecture, trained with different loss functions. We show that, when used for adversarial data augmentation, our perturbations result in trained models that are more robust, without sacrificing overall accuracy of the model. This is unlike what has been observed in image classification, where adding the perturbed images to the training set makes the model less vulnerable to adversarial perturbations, but to the detriment of overall accuracy. We test our method using the most recent stereo networks and evaluate their performance on public benchmark datasets.

We propose a deep neural network architecture to infer dense depth from an image and a sparse point cloud. It is trained using a video stream and corresponding synchronized sparse point cloud, as obtained from a LIDAR or other range sensor, along with the intrinsic calibration parameters of the camera. At inference time, the calibration of the camera, which can be different than the one used for training, is fed as an input to the network along with the sparse point cloud and a single image. A Calibrated Backprojection Layer backprojects each pixel in the image to three-dimensional space using the calibration matrix and a depth feature descriptor. The resulting 3D positional encoding is concatenated with the image descriptor and the previous layer output to yield the input to the next layer of the encoder. A decoder, exploiting skip-connections, produces a dense depth map. The resulting Calibrated Backprojection Network, or KBNet, is trained without supervision by minimizing the photometric reprojection error. KBNet imputes missing depth value based on the training set, rather than on generic regularization. We test KBNet on public depth completion benchmarks, where it outperforms the state of the art by 30% indoor and 8% outdoor when the same camera is used for training and testing. When the test camera is different, the improvement reaches 62%.

We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene. We show that such perturbations can not only globally re-scale the predicted distances from the camera, but also alter the prediction to match a different target scene. We also show that, when given semantic or instance information, perturbations can fool the network to alter the depth of specific categories or instances in the scene, and even remove them while preserving the rest of the scene. To understand the effect of targeted perturbations, we conduct experiments on state-of-the-art monocular depth prediction methods. Our experiments reveal vulnerabilities in monocular depth prediction networks, and shed light on the biases and context learned by them.

We present a deep learning system to infer the posterior distribution of a dense depth map associated with an image, by exploiting sparse range measurements, for instance from a lidar. While the lidar may provide a depth value for a small percentage of the pixels, we exploit regularities reflected in the training set to complete the map so as to have a probability over depth for each pixel in the image. We exploit a Conditional Prior Network, that allows associating a probability to each depth value given an image, and combine it with a likelihood term that uses the sparse measurements. Optionally we can also exploit the availability of stereo during training, but in any case only require a single image and a sparse point cloud at run-time. We test our approach on both unsupervised and supervised depth completion using the KITTI benchmark, and improve the state-of-the-art in both.

Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene structure without direct supervision. Although we train a network with stereo pairs, we only require a single image at test time to hypothesize disparity or depth. We propose a novel objective function that exploits the bilateral cyclic relationship between the left and right disparities and we introduce an adaptive regularization scheme that allows the network to handle both the co-visible and occluded regions in a stereo pair. This process ultimately produces a model to generate hypotheses for the 3-dimensional structure of the scene as viewed in a single image. When used to generate a single (most probable) estimate of depth, our method outperforms state-of-the-art unsupervised monocular depth prediction methods on the KITTI benchmarks. We show that our method generalizes well by applying our models trained on KITTI to the Make3d dataset.

The task of discriminating one object from another is almost trivial for a human being. However, this task is computationally taxing for most modern machine learning methods, whereas, we perform this task at ease given very few examples for learning. It has been proposed that the quick grasp of concept may come from the shared knowledge between the new example and examples previously learned. We believe that the key to one-shot learning is the sharing of common parts as each part holds immense amounts of information on how a visual concept is constructed. We propose an unsupervised method for learning a compact dictionary of image patches representing meaningful components of an objects. Using those patches as features, we build a compositional model that outperforms a number of popular algorithms on a one-shot learning task. We demonstrate the effectiveness of this approach on hand-written digits and show that this model generalizes to multiple datasets.

Clustering is a popular problem with many applications. We consider the k-means problem in the situation where the data is too large to be stored in main memory and must be accessed sequentially, such as from a disk, and where we must use as little memory as possible. Our algorithm is based on recent theoretical results, with significant improvements to make it practical. Our approach greatly simpli(cid:173) fies a recently developed algorithm, both in design and in analysis, and eliminates large constant factors in the approximation guarantee, the memory requirements, and the running time. We then incorporate approximate nearest neighbor search to compute k-means in o(nk) (where n is the number of data points; note that com(cid:173) puting the cost, given a solution, takes 8(nk) time). We show that our algorithm compares favorably to existing algorithms - both theoretically and experimentally, thus providing state-of-the-art performance in both theory and practice.