Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in either limits the performance of VLMs. Prior efforts to enhance reasoning often depend on high-quality chain-of-thought (CoT) data, obtained via labor-intensive human annotations, costly proprietary models or self-training methods that overlook perception. To address these limitations, we propose a simple yet effective self-training framework called "See-Think-Learn" (STL). At its core, STL introduces a structured reasoning template that encourages the model to see before thinking: first extracting visual attributes in textual form, then using them to guide reasoning. The framework jointly improves perception and reasoning by having the model generate and learn from its own structured rationales in a self-training loop. Furthermore, we augment the training data with negative rationales, i.e. explanations that justify why certain answer choices are incorrect, to enhance the model’s ability to distinguish between correct and misleading responses. This fosters more discriminative and robust learning. Experiments across diverse domains show that STL consistently outperforms baselines trained directly only on answers or self-generated reasoning, while qualitative analysis confirms the high quality of its rationales. STL thus provides a cost-effective solution to enhance multimodal reasoning ability of VLMs. Our code is available at https://github.com/srbhcs/see-think-learn.

In recent years, there have been advancements in developing Depth-Image-Based Rendering (DIBR) views. However, the quality of these synthesized views is often degraded by inefficient in-painting techniques and synthesis procedures, leading to geometric and structural distortions. This paper introduces two novel approaches to evaluate the quality of DIBR synthesized views, using full reference (FR) and no-reference (NR) metrics. The proposed FR quality assessment (QA) metric is based on the observation that the deep features of the Non-Subsampled Contourlet Transform (NSCT) maps capture the perceptually important characteristics of the images. By calculating the difference between these deep feature vectors of the reference and distorted views, we determine the quality of the image. Moreover, a lot of existing NR metrics typically divide an image into blocks and assign the same subjective quality scores to each block for training a deep learning model. However, this approach is not suitable for DIBR synthesized views, as distortions are often localized in specific areas rather than affecting the entire view. Consequently, the performance of existing block-based deep-learning algorithms suffers due to the absence of accurate ground truth scores for each image block. To address this limitation, this work proposes an innovative method for calculating ground truth scores for individual image blocks. This process is similar to the proposed FR metric. Firstly, we obtain the deep features of NSCT map of an image block and the quality score for each block is calculated using its and the reference block's feature vector. These block-wise ground truth scores are used to train a deep learning model which serves as an NR metric for estimating the quality of a given test block. Finally, the predicted block-level quality values are aggregated to determine the overall quality of the entire image. Experimental results demonstrate that both the proposed algorithms perform better than the existing objective metrics for DIBR synthesized views.

The advancement in Image-to-Image translation techniques using generative Deep Learning-based approaches has shown promising results for the challenging task of inpainting-based 3D view synthesis. At the same time, even the current 3D view synthesis methods often create distorted structures or blurry textures inconsistent with surrounding areas. We analyzed the recently proposed algorithms for inpainting-based 3D view synthesis and observed that these algorithms no longer produce stretching and black holes. However, the existing databases such as IETR, IRCCyN, and IVY have 3D-generated views with these artifacts. This observation suggests that the existing 3D view synthesis quality assessment algorithms can not judge the quality of most recent 3D synthesized views. With this view, through this abstract, we analyze the need for a new large-scale database and a new perceptual quality metric oriented for 3D views using a test dataset.

Quality assessment of 3D-synthesized images has traditionally been based on detecting specific categories of distortions such as stretching, black-holes, blurring, etc. However, such approaches have limitations in accurately detecting distortions entirely in 3D synthesized images affecting their performance. This work proposes an algorithm to efficiently detect the distortions and subsequently evaluate the perceptual quality of 3D synthesized images. The process of generation of 3D synthesized images produces a few pixel shift between reference and 3D synthesized image, and hence they are not properly aligned with each other. To address this, we propose using morphological operation (opening) in the residual image to reduce perceptually unimportant information between the reference and the distorted 3D synthesized image. The residual image suppresses the perceptually unimportant information and highlights the geometric distortions which significantly affect the overall quality of 3D synthesized images. We utilized the information present in the residual image to quantify the perceptual quality measure and named this algorithm as Perceptually Unimportant Information Reduction (PU-IR) algorithm. At the same time, the residual image cannot capture the minor structural and geometric distortions due to the usage of erosion operation. To address this, we extract the perceptually important deep features from the pre-trained VGG-16 architectures on the Laplacian pyramid. The distortions in 3D synthesized images are present in patches, and the human visual system perceives even the small levels of these distortions. With this view, to compare these deep features between reference and distorted image, we propose using cosine similarity and named this algorithm as Deep Features extraction and comparison using Cosine Similarity (DF-CS) algorithm. The cosine similarity is based upon their similarity rather than computing the magnitude of the difference of deep features. Finally, the pooling is done to obtain the objective quality scores using simple multiplication to both PU-IR and DF-CS algorithms. Our source code is available online: https://github.com/sadbhawnathakur/3D-Image-Quality-Assessment.

Existing Quality Assessment (QA) algorithms consider identifying "black-holes" to assess perceptual quality of 3D-synthesized views. However, advancements in rendering and inpainting techniques have made black-hole artifacts near obsolete. Further, 3D-synthesized views frequently suffer from stretching artifacts due to occlusion that in turn affect perceptual quality. Existing QA algorithms are found to be inefficient in identifying these artifacts, as has been seen by their performance on the IETR dataset. We found, empirically, that there is a relationship between the number of blocks with stretching artifacts in view and the overall perceptual quality. Building on this observation, we propose a Convolutional Neural Network (CNN) based algorithm that identifies the blocks with stretching artifacts and incorporates the number of blocks with the stretching artifacts to predict the quality of 3D-synthesized views. To address the challenge with existing 3D-synthesized views dataset, which has few samples, we collect images from other related datasets to increase the sample size and increase generalization while training our proposed CNN-based algorithm. The proposed algorithm identifies blocks with stretching distortions and subsequently fuses them to predict perceptual quality without reference, achieving improvement in performance compared to existing no-reference QA algorithms that are not trained on the IETR dataset. The proposed algorithm can also identify the blocks with stretching artifacts efficiently, which can further be used in downstream applications to improve the quality of 3D views. Our source code is available online: https://github.com/sadbhawnathakur/3D-Image-Quality-Assessment.

We propose a two-stage Convolutional Neural Network (CNN) based classification framework for detecting COVID-19 and Community Acquired Pneumonia (CAP) using the chest Computed Tomography (CT) scan images. In the first stage, an infection - COVID-19 or CAP, is detected using a pre-trained DenseNet architecture. Then, in the second stage, a fine-grained three-way classification is done using EfficientNet architecture. The proposed COVID+CAP-CNN framework achieved a slice-level classification accuracy of over 94% at identifying COVID-19 and CAP. Further, the proposed framework has the potential to be an initial screening tool for differential diagnosis of COVID-19 and CAP, achieving a validation accuracy of over 89.3% at the finer three-way COVID-19, CAP, and healthy classification. Within the IEEE ICASSP 2021 Signal Processing Grand Challenge (SPGC) on COVID-19 Diagnosis, our proposed two-stage classification framework achieved an overall accuracy of 90% and sensitivity of .857, .9, and .942 at distinguishing COVID-19, CAP, and normal individuals respectively, to rank first in the evaluation. Code and model weights are available at https://github.com/shubhamchaudhary2015/ct_covid19_cap_cnn

In the literature, many 3D-Synthesized Image Quality Assessment (IQA) algorithms are proposed, which are based on predicting the geometric and structural distortions present in the synthesized datasets. With the exponential growth of accurate inpainting algorithms, certain types of distortions, such as Blackholes, has become obsolete. Unfortunately, the existing IQA algorithms are mainly concentrating on efficiently identifying these black holes and subsequently predicting the perceptual quality of 3D synthesized views. The performance of these algorithms is quite weak in the recently proposed IETR dataset. Towards this end, we propose a new completely blind IQA algorithm, which is based on the following key observations: 1. Distortions such as blurriness, blockiness (compression artifacts), and fast fading (object shifting) primarily affect the perceptual quality of 3D-synthesized views. 2. The perceptual characteristics of natural and synthetic synthesized views are quite different; distortions in natural views are perceptually more sensitive than the former. 3. Human Visual System's (HVS) ability to access the perceptual quality of an image also depends on some other properties of the images, such as contrast. All these observations are integrated into the proposed algorithm named Distortion-Specific Contrast-Based (DSCB) IQA. Various experiments validate that the proposed DSCB IQA efficiently competes with human perception and exhibits substantially better results (at least 17% gain in terms of PLCC) when compared to the existing NR IQAs.