We introduce InseRF, a novel method for generative object insertion in the NeRF reconstructions of 3D scenes. Based on a user-provided textual description and a 2D bounding box in a reference viewpoint, InseRF generates new objects in 3D scenes. Recently, methods for 3D scene editing have been profoundly transformed, owing to the use of strong priors of text-to-image diffusion models in 3D generative modeling. Existing methods are mostly effective in editing 3D scenes via style and appearance changes or removing existing objects. Generating new objects, however, remains a challenge for such methods, which we address in this study. Specifically, we propose grounding the 3D object insertion to a 2D object insertion in a reference view of the scene. The 2D edit is then lifted to 3D using a single-view object reconstruction method. The reconstructed object is then inserted into the scene, guided by the priors of monocular depth estimation methods. We evaluate our method on various 3D scenes and provide an in-depth analysis of the proposed components. Our experiments with generative insertion of objects in several 3D scenes indicate the effectiveness of our method compared to the existing methods. InseRF is capable of controllable and 3D-consistent object insertion without requiring explicit 3D information as input. Please visit our project page at https://mohamad-shahbazi.github.io/inserf.
Foundational vision-language models such as CLIP are becoming a new paradigm in vision, due to their excellent generalization abilities. However, adapting these models for downstream tasks while maintaining their generalization remains a challenge. In literature, one branch of methods adapts CLIP by learning prompts using visual information. While effective, most of these works require labeled data which is not practical, and often struggle to generalize towards new datasets due to over-fitting on the source data. An alternative approach resorts to training-free methods by generating class descriptions from large language models (LLMs) and perform prompt ensembling. However, these methods often generate class specific prompts that cannot be transferred to other classes, which incur higher costs by generating LLM descriptions for each class separately. In this work, we propose to combine the strengths of these both streams of methods by learning prompts using only text data derived from LLMs. As supervised training of prompts is not trivial due to absence of images, we develop a training approach that allows prompts to extract rich contextual knowledge from LLM data. Moreover, with LLM contextual data mapped within the learned prompts, it enables zero-shot transfer of prompts to new classes and datasets potentially cutting the LLM prompt engineering cost. To the best of our knowledge, this is the first work that learns generalized prompts using text only data. We perform extensive evaluations on 4 benchmarks where our method improves over prior ensembling works while being competitive to those utilizing labeled images. Our code and pre-trained models are available at https://github.com/muzairkhattak/ProText.
Local image feature descriptors have had a tremendous impact on the development and application of computer vision methods. It is therefore unsurprising that significant efforts are being made for learning-based image point descriptors. However, the advantage of learned methods over handcrafted methods in real applications is subtle and more nuanced than expected. Moreover, handcrafted descriptors such as SIFT and SURF still perform better point localization in Structure-from-Motion (SfM) compared to many learned counterparts. In this paper, we propose a very simple and effective approach to learning local image descriptors by using a hand-crafted detector and descriptor. Specifically, we choose to learn only the descriptors, supported by handcrafted descriptors while discarding the point localization head. We optimize the final descriptor by leveraging the knowledge already present in the handcrafted descriptor. Such an approach of optimization allows us to discard learning knowledge already present in non-differentiable functions such as the hand-crafted descriptors and only learn the residual knowledge in the main network branch. This offers 50X convergence speed compared to the standard baseline architecture of SuperPoint while at inference the combined descriptor provides superior performance over the learned and hand-crafted descriptors. This is done with minor increase in the computations over the baseline learned descriptor. Our approach has potential applications in ensemble learning and learning with non-differentiable functions. We perform experiments in matching, camera localization and Structure-from-Motion in order to showcase the advantages of our approach.
The opacity of rigid 3D scenes with opaque surfaces is considered to be of a binary type. However, we observed that this property is not followed by the existing RGB-only NeRF-SLAM. Therefore, we are motivated to introduce this prior into the RGB-only NeRF-SLAM pipeline. Unfortunately, the optimization through the volumetric rendering function does not facilitate easy integration of the desired prior. Instead, we observed that the opacity of ternary-type (TT) is well supported. In this work, we study why ternary-type opacity is well-suited and desired for the task at hand. In particular, we provide theoretical insights into the process of jointly optimizing radiance and opacity through the volumetric rendering process. Through exhaustive experiments on benchmark datasets, we validate our claim and provide insights into the optimization process, which we believe will unleash the potential of RGB-only NeRF-SLAM. To foster this line of research, we also propose a simple yet novel visual odometry scheme that uses a hybrid combination of volumetric and warping-based image renderings. More specifically, the proposed hybrid odometry (HO) additionally uses image warping-based coarse odometry, leading up to an order of magnitude final speed-up. Furthermore, we show that the proposed TT and HO well complement each other, offering state-of-the-art results on benchmark datasets in terms of both speed and accuracy.
The Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) due to its well suited compatibility to downstream tasks. For the enhanced safety of AVs, modeling perception uncertainty in BEV is crucial. Recent diffusion-based methods offer a promising approach to uncertainty modeling for visual perception but fail to effectively detect small objects in the large coverage of the BEV. Such degradation of performance can be attributed primarily to the specific network architectures and the matching strategy used when training. Here, we address this problem by combining the diffusion paradigm with current state-of-the-art 3D object detectors in BEV. We analyze the unique challenges of this approach, which do not exist with deterministic detectors, and present a simple technique based on object query interpolation that allows the model to learn positional dependencies even in the presence of the diffusion noise. Based on this, we present a diffusion-based DETR model for object detection that bears similarities to particle methods. Abundant experimentation on the NuScenes dataset shows equal or better performance for our generative approach, compared to deterministic state-of-the-art methods. Our source code will be made publicly available.
Understanding the decision-making process of drivers is one of the keys to ensuring road safety. While the driver intent and the resulting ego-motion trajectory are valuable in developing driver-assistance systems, existing methods mostly focus on the motions of other vehicles. In contrast, we focus on inferring the ego trajectory of a driver's vehicle using their gaze data. For this purpose, we first collect a new dataset, GEM, which contains high-fidelity ego-motion videos paired with drivers' eye-tracking data and GPS coordinates. Next, we develop G-MEMP, a novel multimodal ego-trajectory prediction network that combines GPS and video input with gaze data. We also propose a new metric called Path Complexity Index (PCI) to measure the trajectory complexity. We perform extensive evaluations of the proposed method on both GEM and DR(eye)VE, an existing benchmark dataset. The results show that G-MEMP significantly outperforms state-of-the-art methods in both benchmarks. Furthermore, ablation studies demonstrate over 20% improvement in average displacement using gaze data, particularly in challenging driving scenarios with a high PCI. The data, code, and models can be found at https://eth-ait.github.io/g-memp/.
Learning-based point cloud registration approaches have significantly outperformed their traditional counterparts. However, they typically require extensive training on specific datasets. In this paper, we propose , the first zero-shot point cloud registration approach that eliminates the need for training on point cloud datasets. The cornerstone of ZeroReg is the novel transfer of image features from keypoints to the point cloud, enriched by aggregating information from 3D geometric neighborhoods. Specifically, we extract keypoints and features from 2D image pairs using a frozen pretrained 2D backbone. These features are then projected in 3D, and patches are constructed by searching for neighboring points. We integrate the geometric and visual features of each point using our novel parameter-free geometric decoder. Subsequently, the task of determining correspondences between point clouds is formulated as an optimal transport problem. Extensive evaluations of ZeroReg demonstrate its competitive performance against both traditional and learning-based methods. On benchmarks such as 3DMatch, 3DLoMatch, and ScanNet, ZeroReg achieves impressive Recall Ratios (RR) of over 84%, 46%, and 75%, respectively.
Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content, specialize to user data through few-shot fine-tuning, and condition their output on other modalities, such as semantic maps. However, are they usable as large-scale data generators, e.g., to improve tasks in the perception stack, like semantic segmentation? We investigate this question in the context of autonomous driving, and answer it with a resounding "yes". We propose an efficient data generation pipeline termed DGInStyle. First, we examine the problem of specializing a pretrained LDM to semantically-controlled generation within a narrow domain. Second, we design a Multi-resolution Latent Fusion technique to overcome the bias of LDMs towards dominant objects. Third, we propose a Style Swap technique to endow the rich generative prior with the learned semantic control. Using DGInStyle, we generate a diverse dataset of street scenes, train a domain-agnostic semantic segmentation model on it, and evaluate the model on multiple popular autonomous driving datasets. Our approach consistently increases the performance of several domain generalization methods, in some cases by +2.5 mIoU compared to the previous state-of-the-art method without our generative augmentation scheme. Source code and dataset are available at https://dginstyle.github.io .
Understanding human activity is a crucial yet intricate task in egocentric vision, a field that focuses on capturing visual perspectives from the camera wearer's viewpoint. While traditional methods heavily rely on representation learning trained on extensive video data, there exists a significant limitation: obtaining effective video representations proves challenging due to the inherent complexity and variability in human activities.Furthermore, exclusive dependence on video-based learning may constrain a model's capability to generalize across long-tail classes and out-of-distribution scenarios. In this study, we introduce a novel approach for long-term action anticipation using language models (LALM), adept at addressing the complex challenges of long-term activity understanding without the need for extensive training. Our method incorporates an action recognition model to track previous action sequences and a vision-language model to articulate relevant environmental details. By leveraging the context provided by these past events, we devise a prompting strategy for action anticipation using large language models (LLMs). Moreover, we implement Maximal Marginal Relevance for example selection to facilitate in-context learning of the LLMs. Our experimental results demonstrate that LALM surpasses the state-of-the-art methods in the task of long-term action anticipation on the Ego4D benchmark. We further validate LALM on two additional benchmarks, affirming its capacity for generalization across intricate activities with different sets of taxonomies. These are achieved without specific fine-tuning.
In this paper, we showcase the effectiveness of optimizing monocular camera poses as a continuous function of time. The camera poses are represented using an implicit neural function which maps the given time to the corresponding camera pose. The mapped camera poses are then used for the downstream tasks where joint camera pose optimization is also required. While doing so, the network parameters -- that implicitly represent camera poses -- are optimized. We exploit the proposed method in four diverse experimental settings, namely, (1) NeRF from noisy poses; (2) NeRF from asynchronous Events; (3) Visual Simultaneous Localization and Mapping (vSLAM); and (4) vSLAM with IMUs. In all four settings, the proposed method performs significantly better than the compared baselines and the state-of-the-art methods. Additionally, using the assumption of continuous motion, changes in pose may actually live in a manifold that has lower than 6 degrees of freedom (DOF) is also realized. We call this low DOF motion representation as the \emph{intrinsic motion} and use the approach in vSLAM settings, showing impressive camera tracking performance.